Vibe Coding DiscoverCategory
AI Coding
Coding agents, IDE assistants, and software engineering automations.
| Project name | Stars | Category | Language | Tags | Summary | View Project |
|---|---|---|---|---|---|---|
| opencode | ★ 211K | AI Coding | TypeScript | coding agent · AI coding · terminal · desktop app · code editing · codebase exploration · multi-agent · developer tool | Open-source AI coding agent available in the terminal and as a desktop app. Includes build and read-only planning agents, plus a general subagent for complex searches and tasks. | View Project → |
| claw-code | ★ 195K | AI Coding | Rust | rust · cli · agent-harness · mcp · acp · agent-skills · session-management · llm-cli · openai-compatible · docker · self-maintained · reference-implementation | Rust implementation of the `claw` CLI agent harness, published as an agent-managed museum exhibit rather than a production product. Offers prompt/session CLI, MCP plugin lifecycle, ACP status, Docker and Windows workflows; build-from-source only, with LazyCodex/Gajae-Code as the real harnesses. | View Project → |
| claude-code | ★ 148K | AI Coding | TypeScript | claude · agentic-coding · terminal · cli · developer-tools · code-assistant · git-workflows · ide-integration · plugins · anthropic · natural-language · codebase-understanding | Anthropic's official agentic coding tool that runs in your terminal or IDE, reads your codebase, and executes tasks, git workflows, and code explanations from natural-language prompts. Includes plugin support for custom commands and agents. | View Project → |
| spec-kit | ★ 138K | AI Coding | Python | spec-driven-development · ai-coding-agent · agent-skills · slash-commands · templates · prd · workflow · cli · github-copilot · extensions · presets · bundles · planning · developer-tooling | GitHub Spec Kit is a Python CLI plus agent skill packs that give AI coding agents a structured spec-driven workflow: define a spec, plan, tasks, then implement and converge, with optional bug-fixing and idea-assessment extensions. | View Project → |
| codex | ★ 126K | AI Coding | Rust | coding-agent · cli · terminal · rust · openai · sandbox · mcp · agent-skills · slash-commands · code-execution · non-interactive-exec · full-auto · ide-integration · chatgpt-auth · apache-2.0 · agent-policy | Codex CLI is OpenAI's lightweight open-source coding agent that runs locally in your terminal, written in Rust. It reads and edits code, runs shell commands in a sandbox, supports MCP servers, skills, and scriptable `codex exec`, and can sign in with a ChatGPT plan or API key. | View Project → |
| pi | ★ 109K | AI Coding | TypeScript | coding-agent · cli · tui · agent-runtime · unified-llm-api · tool-calling · monorepo · typescript · self-extensible · terminal · sandboxing · containerization · model-catalog · session-management · state-management | Pi is a TypeScript monorepo agent harness: an interactive coding-agent CLI, an agent runtime with tool calling/state, a unified multi-provider LLM API, and a differential-rendering TUI. MIT licensed and self-extensible via custom providers and sandbox extensions. | View Project → |
| gemini-cli | ★ 107K | AI Coding | TypeScript | cli · terminal-agent · gemini · mcp-client · ai-agent · code-generation · sandboxing · headless-mode · google-search-grounding · typescript · apache-2.0 · context-files · checkpointing · vscode-companion | Google's open-source AI coding agent for the terminal, built on Gemini with 1M-token context. Supports file/shell/web tools, MCP servers, sandboxing, headless scripting and a VS Code companion. | View Project → |
| OpenHands | ★ 89K | AI Coding | TypeScript | coding-agents · self-hosted · agent-canvas · acp · claude-code · codex · automations · webhooks · slack · github · docker-sandbox · multi-backend · electron · cli · control-center · developer-tools | OpenHands Agent Canvas is a self-hosted control center UI for running coding agents (OpenHands, Claude Code, Codex, Gemini, any ACP agent) across local, Docker, VM, and cloud backends, with scheduled and event-driven automations wired into Slack, GitHub, and Linear. | View Project → |
| OpenHands | ★ 89K | AI Coding | TypeScript | Python · Coding Agent · OpenHands | Open platform for software agents that write, run, and debug code like a developer. | View Project → |
| orca | ★ 75K | AI Coding | TypeScript | agent-ide · parallel-agents · agent-orchestration · git-worktrees · terminal · claude-code · codex · opencode · computer-use · mobile-companion · ssh-remote · code-review · cli · electron · workflow-automation · multi-agent | Orca is a desktop/mobile Agent Development Environment for running many coding agents (Claude Code, Codex, OpenCode, Cursor, etc.) in parallel git worktrees under your own subscription. It adds terminals, diff review, GitHub/Linear integration, SSH remote runtimes, a CLI and computer-use control. | View Project → |
| codegraph | ★ 72K | AI Coding | C | code-graph · code-intelligence · knowledge-graph · static-analysis · tree-sitter · mcp-server · local-first · context-engineering · code-indexing · multi-language · dead-code-detection · auto-sync · cli · agent-context | CodeGraph builds a local, pre-indexed code knowledge graph and exposes it to coding agents (Claude Code, Cursor, Codex, Copilot, Gemini and more) via an MCP server, auto-syncing on file changes. It returns surgical cross-file context to cut tokens and tool calls, and runs 100% locally with no cloud dependency. | View Project → |
| OpenSpec | ★ 70K | AI Coding | TypeScript | spec-driven-development · sdd · ai-coding · context-engineering · slash-commands · cli · planning · prd · agent-skills · sdlc · brownfield · markdown · developer-tools · workflow · typescript · npm | OpenSpec is a Node CLI plus slash-command workflow that adds a Markdown spec layer to AI coding assistants: you propose a change, review generated proposal/specs/design/tasks, then let the agent implement and archive it. Works across 30+ tools and brownfield repos. | View Project → |
| cline | ★ 69K | AI Coding | TypeScript | autonomous-agent · coding-agent · ide-extension · cli · vscode · jetbrains · sdk · mcp · multi-agent · computer-use · headless-ci · scheduled-tasks · human-in-the-loop · plan-and-act · checkpoints · typescript | Cline is an open source autonomous coding agent available as a VS Code/JetBrains extension, terminal CLI, desktop app, and Node SDK. It plans and executes edits, runs shell commands, supports MCP servers, multi-agent teams, scheduled runs, and any model provider. | View Project → |
| openinterpreter | ★ 68K | AI Coding | Rust | coding-agent · terminal · open-models · Rust · ACP · MCP · sandboxing · computer-use · skills · harnesses | A Rust terminal coding agent that emulates multiple agent harnesses for low-cost and open models. It supports sandboxed command execution, ACP and MCP, shared agent skills, and computer-use testing. | View Project → |
| claude-code-best-practice | ★ 66K | AI Coding | HTML | Claude Code · best practices · agentic coding · agent teams · subagents · skills · commands · MCP · workflows · context engineering | A practical guide and example repository for Claude Code, covering setup, commands, skills, subagents, MCP, memory, and agent orchestration. Includes implementation examples and workflow documentation for developers adopting agentic coding. | View Project → |
| warp | ★ 65K | AI Coding | Rust | terminal · coding-agent · agentic-dev-environment · cli-agents · multi-agent · rust · mcp · computer-use · shell · bash · zsh · wasm · developer-productivity · code-review · issue-triage · open-source | Warp is an agentic development environment built on the terminal, written in Rust. It ships a built-in coding agent, lets you plug in external CLI agents like Claude Code, Codex and Gemini CLI, and powers agent 'Factories' that triage issues, write specs, implement changes and review PRs. | View Project → |
| free-claude-code | ★ 56K | AI Coding | Python | claude-code · codex · coding-agents · llm-proxy · multi-model · openai-compatible · free-tier · model-router · fallback-models · terminal · browser-sessions · voice-input · aider · cline · opencode · provider-catalog | Local Python proxy that connects 10 coding agents (Claude Code, Codex, Cline, Aider, OpenCode and more) to 53 OpenAI-compatible providers in one model catalog, with automatic model fallback, browser Code sessions, voice input, and IDE/chat-client launchers. | View Project → |
| gpt-engineer | ★ 55K | AI Coding | Python | Python · Codegen · Agent | Specify an app in natural language; the agent clarifies, then generates the codebase. | View Project → |
| gpt-engineer | ★ 55K | AI Coding | Python | code-generation · cli · autonomous-agent · coding-assistant · codebase-generation · python · openai · anthropic · vision · benchmark · preprompts · local-models | CLI (gpte) that turns a natural-language prompt into a working codebase, then iteratively improves existing code. Supports OpenAI/Azure/Anthropic and local open models, plus a benchmark harness for APPS and MBPP. | View Project → |
| BMAD-METHOD | ★ 54K | AI Coding | Python | AI coding · agent skills · agile development · spec-driven development · context engineering · software delivery · multi-agent workflows · Claude Code · Codex | An installable skills and workflow method for AI coding tools that guides software work from clarification and planning through implementation and verification. It scales the process to the change and preserves decisions as project context. | View Project → |
| aider | ★ 49K | AI Coding | Python | ai-pair-programming · cli · terminal · code-generation · git-integration · repo-map · multi-llm · voice-to-code · code-editing · developer-tools · linting · local-llms | Aider is a terminal CLI that pairs you with an LLM to edit code in your local git repo. It maps your codebase, applies diffs across 100+ languages, auto-commits with git, and runs lint/tests, supporting Claude, GPT, DeepSeek, Gemini and local models. | View Project → |
| open-code-review | ★ 43K | AI Coding | Go | code-review · cli · llm-agent · static-analysis · diff-review · security-rules · github-actions · ci-cd · mcp-server · agent-skills · go · multi-language · line-level-comments · pull-request · tool-use | Alibaba's AI code review CLI in Go: a deterministic pipeline (file selection, bundling, rule matching) plus an LLM agent with tool use produces precise line-level review comments. Works on git diffs, branch ranges or full-file scans, supports OpenAI/Anthropic-compatible endpoints and plugins for Claude Code, Codex, Cur | View Project → |
| Codewhale | ★ 41K | AI Coding | Rust | coding-agent · terminal · tui · rust · mcp · multi-agent · local-first · cli · computer-use · agent-orchestration · multi-model · hooks · skills · sandboxing · self-hosted · open-source | Codewhale is a Rust-based open-source terminal coding agent that reads your repo, edits files, runs commands, and verifies its work using hosted or local models. It supports multi-agent teams, MCP servers, skills, hooks, approval modes, and a local runtime with TUI, web, and VS Code clients. | View Project → |
| claude-plugins-official | ★ 37K | AI Coding | Python | Claude Code · plugin directory · marketplace · MCP · agent definitions · skills · slash commands | Anthropic-managed marketplace directory for Claude Code plugins, including extensions with slash commands, agents, skills, and optional MCP server configurations. Browse or install entries through Claude Code's plugin system. | View Project → |
| continue | ★ 36K | AI Coding | TypeScript | coding-agent · ide-assistant · vscode-extension · jetbrains-plugin · cli · autocomplete · chat · code-editing · open-source · developer-tools · typescript · model-agnostic · local-models · custom-rules · agent | Continue is an open-source coding agent delivered as a CLI, VS Code extension, and JetBrains plugin for chat, autocomplete, and agentic code edits. The repo is now read-only after a final 2.0.0 release, so treat it as a reference codebase rather than an actively maintained tool. | View Project → |
| DeepSeek-Reasonix | ★ 36K | AI Coding | Go | coding-agent · terminal · tui · cli · deepseek · prompt-caching · prefix-cache · mcp · plugins · acp · subagents · checkpoints · sandbox · go · vscode-extension · desktop-app | Reasonix is a DeepSeek-native coding agent (Go, MIT) that runs in your terminal, desktop, browser, or editor over ACP. It focuses on prefix-cache stability for long runs, with plan mode, permissions, workspace sandbox, checkpoints, MCP plugins, and config-driven providers/models. | View Project → |
| tabby | ★ 34K | AI Coding | Rust | self-hosted · code-completion · coding-assistant · copilot-alternative · on-premises · ide-extension · vscode · jetbrains · vim · chat-in-ide · repository-context · openapi · gpu-inference · code-llm · enterprise · rust | Self-hosted AI coding assistant and open-source Copilot alternative: inline code completion, IDE chat, and a RAG answer engine over your repos and internal docs. Ships a Rust server with OpenAI-compatible APIs, supports consumer GPUs, and needs no external DB or cloud. | View Project → |
| oh-my-codex | ★ 33K | AI Coding | TypeScript | codex-cli · multi-agent · orchestration · agent-teams · skills · hooks · cli · workflow · tmux · hud · agents-md · developer-tools · prompt-workflows · mcp · cli-tooling · typescript | OMX is a TypeScript workflow layer for the OpenAI Codex CLI: it adds prompt workflows ($plan, $ultragoal, $team, $code-review), lifecycle hooks, specialist agent teams, HUDs, skills, and .omx/ durable state around your existing Codex install. | View Project → |
| oh-my-pi | ★ 32K | AI Coding | TypeScript | coding-agent · terminal · tui · cli · lsp · dap · debugger · mcp · subagents · multi-provider · rust · bun · typescript · code-review · collaboration · native | oh-my-pi (omp) is a terminal coding agent that wires in IDE-grade capabilities: LSP, DAP debuggers, in-process ripgrep, subagents, an advisor reviewer model, and 60+ LLM providers. Rust core plus Bun/TypeScript TUI. | View Project → |
| claude-code-templates | ★ 31K | AI Coding | Python | claude-code · cli · templates · ai-agents · mcp · skills · slash-commands · hooks · subagents · developer-tools · anthropic · configuration · session-analytics · monitoring · plugins | CLI and component catalog for configuring Anthropic's Claude Code: it installs ready-made agents, slash commands, MCP integrations, settings, hooks, and skills, plus analytics and monitoring of Claude Code sessions. | View Project → |
| crush | ★ 28K | AI Coding | Go | coding agent · terminal · LLM · multi-model · MCP · LSP · developer tools · sessions | Crush is a terminal-based AI coding agent that connects to a range of hosted or local LLM providers. It supports project sessions, LSP context, model switching, and MCP integrations over HTTP, stdio, and SSE. | View Project → |
| design.md | ★ 28K | AI Coding | TypeScript | design-tokens · design-system · coding-agents · agent-context · spec · cli · lint · wcag-contrast · tailwind · dtcg · yaml-frontmatter · ui-generation · typescript · google-labs | DESIGN.md is a spec plus CLI that describes a visual identity as YAML design tokens with markdown rationale, so coding agents build UI that matches a brand. Commands lint (contrast, broken refs), diff versions, export to Tailwind/DTCG, and print the spec for agent prompts. | View Project → |
| qwen-code | ★ 28K | AI Coding | TypeScript | ai-coding · coding-agent · cli · terminal · agentic · mcp · subagents · agent-teams · auto-memory · skills · sandbox · headless · multi-model · ide-plugin · sdk · typescript | Qwen Code is an open-source agentic coding agent for the terminal, with IDE plugins, desktop/web UI, SDKs and chat channels. It offers subagents, skills, auto-memory, MCP, sandboxing and multi-provider support (Qwen, OpenAI, Anthropic, Gemini, local Ollama/vLLM). | View Project → |
| beads | ★ 28K | AI Coding | Go | coding agents · agent memory · task tracking · dependency graph · persistent memory · multi-agent workflows · CLI · Dolt | Beads is a CLI-based issue tracker and persistent memory system for coding agents. It stores work in a dependency-aware graph, supports task claiming and multi-agent coordination, and can inject workflow context into agents. | View Project → |
| Roo-Code | ★ 24K | AI Coding | TypeScript | AI coding assistant · VS Code extension · coding agent · multi-agent · code generation · codebase Q&A · debugging · refactoring · custom modes · MCP | A VS Code coding assistant with task-specific modes for coding, architecture, questions, and debugging, plus custom modes and MCP server support. The README states the Roo Code extension was shut down on May 15th. | View Project → |
| prime-agent | ★ 21K | AI Coding | TypeScript | coding-agent · autonomous-agents · subagents · recursive-language-model · self-improving · persistent-repl · long-running-tasks · agent-skills · daemon · tui · agent-to-agent · memory · scheduling · headless-rpc · python-repl · harness | Prime Agent is an MIT-licensed coding/research agent built on a Recursive Language Model harness: a persistent Python REPL drives file ops, shell, tools and recursive subagents. A continual harness refines prompts, memories and skills over time, with daemon-backed sessions for long autonomous runs. | View Project → |
| ai-guide | ★ 21K | AI Coding | JavaScript | vibe coding · AI coding tutorials · AI coding tools · AI agents · MCP · RAG · prompt engineering · OpenClaw · Chinese resources | A Chinese-language AI knowledge base centered on beginner-friendly Vibe Coding tutorials. Covers AI coding tools, hands-on projects, agents, MCP, RAG, prompts, and model guides. | View Project → |
| SWE-agent | ★ 20K | AI Coding | Python | swe-bench · software-engineering · autonomous-agent · github-issues · bug-fixing · computer-use · cybersecurity · ctf · agent-computer-interface · llm · python · research · code-repair · benchmarking · tool-use · neurips | SWE-agent lets a chosen LM autonomously use tools to fix GitHub issues in real repos, hitting state-of-the-art open-source SWE-bench results. It also supports offensive-security (EnIGMA) and competitive coding tasks, configured via YAML. Note: development has moved to mini-SWE-agent. | View Project → |
| jcode | ★ 20K | AI Coding | Rust | coding-agent · tui · cli · rust · multi-model · mcp · agent-memory · embeddings · swarm · terminal · llm · low-memory · session-management · providers · semantic-memory · developer-tools | jcode is a Rust TUI coding agent harness focused on very low RAM and fast startup across many concurrent sessions. It supports multi-model providers, MCP, swarm coordination, and embedding-based semantic agent memory. | View Project → |
| learn-harness-engineering | ★ 16K | AI Coding | TypeScript | harness engineering · AI coding agents · agent reliability · verification workflows · agent state management · context engineering · agent loops · graph engineering · multi-agent workflows · tutorial | A multilingual, project-based course on making AI coding agents more reliable through harness design. Covers instructions, tools, environment, state, verification, automated loops, and graph-based workflows, with lectures, projects, templates, and a harness-creator skill. | View Project → |
| coder | ★ 16K | AI Coding | Go | cloud-development-environments · remote-development · self-hosted · ai-coding-agents · ai-gateway · llm-proxy · mcp · terraform · devcontainers · kubernetes · docker · wireguard · ide-integration · model-governance · audit-logging · go | Self-hosted platform that provisions Terraform-defined cloud dev environments over a secure tunnel and runs AI coding agents in its control plane, with an AI Gateway for model auth, cost tracking, and audit logs. Useful if you want agent-driven coding on your own infra without LLM keys in workspaces. | View Project → |
| cc-haha | ★ 15K | AI Coding | TypeScript | claude-code · coding-agent · multi-agent · mcp · computer-use · electron · desktop-app · skill-marketplace · git-worktree · diff-review · multi-model · im-integration · local-first · typescript · react · scheduled-tasks | Local-first Electron desktop workspace for Claude Code and coding agents: multi-session GUI, Agent Teams, Git worktree/diff review, visual MCP and SubAgent managers, skill marketplace, Computer Use, multi-model support and H5/IM remote access. | View Project → |
| opencode | ★ 14K | AI Coding | Go | terminal · tui · cli · ai-coding-agent · code-assistant · multi-provider · mcp · lsp · session-management · sqlite · shell-execution · non-interactive-mode · go · archived | Archived Go terminal AI coding agent, continued as charmbracelet/crush. Bubble Tea TUI that chats with Claude, GPT, Gemini, Groq, Bedrock or local models; runs shell commands, edits files, uses LSP and MCP servers, and supports non-interactive -p mode. | View Project → |
| pr-agent | ★ 13K | AI Coding | Python | code-review · pull-request · ai-code-review · github-action · gitlab · bitbucket · azure-devops · cli · devtools · automation · self-hosted · pr-description · code-suggestions · llm-agnostic · webhooks · docker | PR-Agent is an open-source AI agent that reviews pull requests: /describe, /review, /improve and /ask commands run via GitHub Action, CLI, or webhooks on GitHub, GitLab, Bitbucket, and Azure DevOps, using any LiteLLM-reachable model. | View Project → |
| pr-agent | ★ 13K | AI Coding | Python | Python · PR Review · Git | AI agent that reviews, describes, and improves pull requests automatically. | View Project → |
| loop-engineering | ★ 11K | AI Coding | TypeScript | loop-engineering · ai-coding-agents · agent-orchestration · claude-code · codex · grok · mcp · cli · github-actions · automation · prompt-engineering · state-persistence · verification · cost-tracking · pattern-library · devops | Pattern library plus TypeScript CLI tools (loop, loop-audit, loop-init, loop-cost) for designing and operating autonomous AI coding agent loops on a repo: triage, PR babysitting, dep updates, changelog. Includes MCP server, pattern registry, and staged L1-L3 safety rollout. | View Project → |
| codex-chatgpt-web | ★ 11K | AI Coding | TypeScript | codex · chatgpt-web · browser-automation · mcp · responses-api · model-bridge · playwright · streaming · subagents · cli · typescript · quota-saving | Local bridge that exposes user-authenticated ChatGPT Web models (including Pro) as native models inside Codex, with streaming, images and MCP tool harness. It enables coding with tools without consuming Codex quota; unofficial browser automation, not an OpenAI API. | View Project → |
| Graft | ★ 9.2K | AI Coding | TypeScript | claude-code · mcp-server · code-graph · context-engineering · knowledge-graph · tree-sitter · codebase-context · cursor · codex · gemini-cli · cli · developer-tools · token-savings · monorepo · blast-radius · code-visualization | Graft is a TypeScript CLI that builds a linked-markdown context graph of your codebase with tree-sitter, then feeds it to Claude Code, Cursor, Codex and other agents via hooks or an MCP server. It aims to cut agent token cost, latency and tool calls while improving multi-file correctness. | View Project → |
| claude-code-action | ★ 9K | AI Coding | TypeScript | GitHub Actions · coding agent · code review · issue triage · PR automation · code changes · Claude Code · CI automation | A GitHub Action that runs Claude Code on issues and pull requests to answer questions, review code, and implement changes. Supports workflow-driven automations and Anthropic API, Amazon Bedrock, Google Vertex AI, and Microsoft Foundry. | View Project → |
| mini-swe-agent | ★ 7.9K | AI Coding | Python | coding-agent · swe-bench · cli · minimal · bash · agent · llm · sandboxing · python · open-source · benchmark · automation | mini-swe-agent is a ~100-line Python software engineering agent that solves GitHub issues and runs as a CLI coding assistant. It uses only bash, has no tool-calling scaffolding, supports any LiteLLM model, and scores >74% on SWE-bench verified. | View Project → |
| kimi-code | ★ 7.7K | AI Coding | TypeScript | cli · coding-agent · terminal · tui · mcp · subagents · acp · plugin-marketplace · hooks · video-input · typescript · monorepo | Kimi Code CLI is a terminal AI coding agent from Moonshot AI that reads and edits code, runs shell commands, searches files and fetches web pages. It ships as a single binary with a fast TUI, MCP config, plugins, subagents and ACP support for Zed/JetBrains. | View Project → |
| gentle-ai | ★ 7.3K | AI Coding | Go | ai-coding · coding-agents · claude-code · cursor · codex · opencode · mcp · agent-skills · persistent-memory · spec-driven-development · code-review · developer-tools · golang · personas · tdd · no-lock-in | Go CLI that configures the AI coding agents you already use (Claude Code, Cursor, Codex, OpenCode, plus 12 more) with persistent memory, Spec-Driven Development workflows, curated skills, MCP servers, personas and optional bounded code review, with no agent lock-in. | View Project → |
| fast-jev-compaction | ★ 6.3K | AI Coding | TypeScript | context-compaction · claude-code · claude-code-plugin · context-window · token-reduction · memory-management · llm-context · session-history · verbatim-context · typescript · npm-library · hooks | Claude Code plugin and npm library that swaps the built-in compaction summary for Jev-scored pruning: every tool call and result is judged in one fast request, stale ones dropped or truncated, kept messages stay verbatim. Falls back to the built-in summary when reduction is too small or Jev fails. | View Project → |
| atlas | ★ 6.2K | AI Coding | TypeScript | ai-coding · coding-agents · multi-agent · claude-code · codex · acp · agent-client-protocol · git · source-control · checkpoints · session-tracking · agent-memory · skills · mcp-client · local-first · self-hosted | Atlas is a desktop source-control layer for coding agents: it runs Claude Code, Codex, Atlas's own agent and ACP registry agents side by side, records every session locally, and links each git commit back to the prompts, tool calls and reasoning behind it. Adds shared on-device memory, skills, knowledge notes and a que | View Project → |
| ouroboros | ★ 6.1K | AI Coding | Python | agent-os · ai-coding-agent · mcp-server · spec-driven-development · llm-orchestration · llm-evaluation · socratic-interview · multi-runtime · claude-code · codex-cli · agentic-loop · workflow-engine · developer-tools · replayable-runs · cli · python | Ouroboros is a local-first Agent OS for AI coding: it replaces ad-hoc prompting with a spec-first loop (interview, crystallize, execute, evaluate, evolve). Ships as an MCP server plus CLI adapters for 14 runtimes including Claude Code, Codex CLI, Gemini CLI and OpenCode. | View Project → |
| PI-Desktop | ★ 5.8K | AI Coding | TypeScript | desktop-app · coding-agent · local-first · electron · rust · mcp · plugins · skills · subagents · multi-model · i18n · session-management · agent-harness · plan-mode · permissions · openai-compatible | PI-Desktop is a local-first Electron + Rust desktop workspace for AI coding agents. Open a local project, connect any model (OpenAI, Anthropic, Ollama, OpenAI-compatible), and let agents read, edit, run commands, and iterate under a permission layer with Agent, Plan, and Goal modes plus plugins, Skills, MCP, and subage | View Project → |
| ZCode | ★ 5.4K | AI Coding | TypeScript | coding-agent · agent-harness · cli · tui · electron · desktop-app · web-ui · monorepo · multi-provider · terminal-agent · code-assistant · rpc · self-hosted · typescript · remote-development · llm-runtime | ZCode is Z.ai's AI coding agent harness shipped as an Electron desktop app, a browser workbench, and a terminal agent (TUI/CLI). It bundles the agent runtime, multi-provider config, RPC layer, and packaging scripts in a TypeScript pnpm monorepo. | View Project → |
| mistral-vibe | ★ 5K | AI Coding | Python | cli · coding-assistant · terminal · mistral · subagents · mcp · skills · slash-commands · tool-permissions · voice-mode · multimodal · opentelemetry · python · developer-tools | Mistral Vibe is Mistral's open-source CLI coding agent in Python. It offers an interactive terminal chat with file edit, shell, grep and git tools, built-in agent profiles, subagents, skills, MCP servers and ACP editor integration. | View Project → |
| claude-code-guide | ★ 4.6K | AI Coding | Python | claude-code · documentation · cheat-sheet · cli · slash-commands · mcp · sub-agents · skills · hooks · configuration · workflows · automation · anthropic · troubleshooting · vscode · best-practices | Community-maintained reference guide for Anthropic's Claude Code CLI: install, slash commands, configuration, MCP integration, sub-agents, skills, hooks, security and troubleshooting. Best as a lookup cheatsheet rather than runnable code. | View Project → |
| Codex-X | ★ 4K | AI Coding | Rust | codex · prompt-management · mcp · skills · provider-switching · session-management · config-editor · tauri · desktop-app · token-usage · toml · cc-switch · rust · cross-platform | Cross-platform desktop GUI (Tauri 2 + React + Rust) for managing OpenAI Codex CLI/desktop: prompt template injection, provider/API switching, session sync, Skills/MCP management, and TOML/auth.json editing with token usage stats. | View Project → |
| lean-ctx | ★ 3.8K | AI Coding | Rust | context-engineering · token-optimization · mcp-server · ai-coding · coding-agents · context-compression · prompt-cache · session-memory · knowledge-graph · rust · local-first · lsp · tree-sitter · cost-tracking · developer-tools · context-layer | Local-first context intelligence layer and MCP server for AI coding agents: it compresses file reads and shell output, routes and remembers context across sessions, and tracks token savings, cost and accepted outcomes via a live dashboard. | View Project → |
| DSH-better-sidebar | ★ 3.8K | AI Coding | TypeScript | DSH · sidebar · AI coding · side chat · subagents · file editor · Git · plugin extensions | A DSH plugin that adds a coding workspace with file browsing and editing, Git and AI-change views, subagent monitoring, and contextual side chats. It also exposes an API for other plugins to register sidebar tabs and file viewers. | View Project → |
| everything-claude-code | ★ 3.6K | AI Coding | JavaScript | claude-code · claude-code-plugin · subagents · slash-commands · hooks · rules · prompt-pack · developer-tooling · tdd · code-review · context-management · session-memory · evals · verification-loops · cross-platform · workflow-automation | Claude Code plugin bundling production-ready subagents, slash commands, skills, hooks, rules, and MCP configs for AI-assisted development. Covers TDD, code/security review, E2E testing, evals, session memory persistence, token optimization, and subagent orchestration. | View Project → |
| ultracite | ★ 3.3K | AI Coding | TypeScript | AI coding · agentic development · linter · formatter · zero-config · TypeScript · monorepo · Claude Code · Codex | A zero-configuration linting and formatting setup for JavaScript and TypeScript projects, with presets for Biome, ESLint, and Oxlint. It can generate shared rules and context files for AI agents and hand unresolved fixes to Claude Code or Codex. | View Project → |
| ripwire | ★ 2.3K | AI Coding | C++ | mcp-server · code-navigation · call-graph · static-analysis · tree-sitter · context-engineering · coding-agents · cli · cpp23 · token-efficiency · impact-analysis · blast-radius · claude-code · codex · diff-review · zero-dependency | Zero-dependency C++23 CLI plus MCP server that builds a deterministic call graph for coding agents, answering callers, uses, impact, tests-to-run and diff-review queries in a fraction of the tokens of grep-and-read. Also installs task-shaped agent skills for Claude Code, Codex, Cursor and others. | View Project → |
| pilot-shell | ★ 2.1K | AI Coding | JavaScript | coding-agents · context-engineering · harness-engineering · persistent-memory · spec-driven-development · test-driven-development · quality-gates · code-review · MCP · human-oversight · runtime-verification · Claude Code · Codex | A harness for Claude Code and OpenAI Codex that adds persistent project context, structured development workflows, quality gates, review, and runtime verification. Includes an installer and a console for human oversight. | View Project → |
| meridian | ★ 2.1K | AI Coding | TypeScript | coding clients · API bridge · Claude · Antigravity · usage dashboard · local proxy · OpenCode · Pi · multi-provider | Meridian runs a local API bridge that lets Pi, OpenCode, and other coding clients use Claude and Antigravity subscriptions. It includes provider management, request monitoring, a usage dashboard, and an optional macOS app. | View Project → |
| nodeterm | ★ 1.9K | AI Coding | TypeScript | AI coding agents · agent orchestration · parallel sessions · terminal manager · tmux · infinite canvas · persistent sessions · kanban · Electron · remote development · Claude Code · Codex · Gemini · OpenCode | A desktop and self-hosted browser workspace for managing persistent terminals and parallel AI coding-agent sessions on a draggable canvas. Supports agents including Claude Code, Codex, Gemini, GitHub Copilot, and OpenCode. | View Project → |
| nimbalyst | ★ 1.8K | AI Coding | TypeScript | coding-agent · multi-agent · claude-code · codex · opencode · mcp · mcp-client · git-worktree · kanban · wysiwyg · markdown-editor · electron · ide · desktop-app · extension-sdk · diff-review | Nimbalyst is an MIT-licensed Electron desktop IDE/workspace for running parallel coding agents (Claude Code, Codex, OpenCode, Copilot) in isolated git worktrees, with visual WYSIWYG editors, diff review, kanban session tracking, task trackers, MCP client support, and an iOS companion. | View Project → |
| minimax-code | ★ 1.8K | AI Coding | TypeScript | coding-agent · terminal · cli · tui · agent-harness · byok · mcp · acp · subagents · plugins · skills · sandboxing · permissions · headless-mode · session-management · typescript | MiniMax Code (mcode) is a TypeScript terminal coding agent that reads files, inspects diffs, runs shell commands and tests, with permission modes and sandboxing. It runs on a MiniMax account or BYOK OpenAI/Anthropic-compatible providers, supports MCP, ACP, subagents, plugins and a headless CLI for CI. | View Project → |
| mex | ★ 1.7K | AI Coding | TypeScript | coding-agents · project-memory · team-memory · context-management · knowledge-graph · code-graph · agent-skills · CLI · Git | MEX stores shared project memory, code-linked knowledge, and teammate handoffs in a Git repository so engineers and coding agents can reuse context across sessions. It provides a CLI, local web Hub, and integrations for Claude Code and Codex. | View Project → |
| happier | ★ 1.7K | AI Coding | TypeScript | coding-agent-orchestration · multi-agent · parallel-sessions · Claude Code · Codex · OpenCode · mobile-control · desktop-app · self-hosted · end-to-end encryption · Git worktrees · MCP | Happier is a web, desktop, and mobile client for running and coordinating coding agents such as Claude Code, Codex, and OpenCode across your machines. It supports parallel sessions, cross-agent delegation, remote control, code review, and self-hosting with end-to-end encryption. | View Project → |
| ai-dev-tools-zoomcamp | ★ 1.6K | AI Coding | Python | AI coding agents · AI-assisted development · software engineering · agent workflows · MCP · agent skills · subagents · testing · CI/CD · DevOps · observability · course | Free, hands-on course materials for using AI coding tools and agents across the software lifecycle. Learners build, test, deploy, monitor, and extend an application with agent workflows, MCP, reusable skills, and subagents. | View Project → |
| ai-devkit | ★ 1.6K | AI Coding | TypeScript | coding-agents · multi-agent · agent-orchestration · cli · tui-console · mcp · agent-skills · local-memory · sqlite · workflow-automation · developer-tools · cross-agent-messaging · verification · tdd · config-reconciliation | TypeScript CLI control plane that gives coding agents (Claude Code, Codex, Gemini CLI, Cursor, and more) one shared config, a live session console, cross-agent messaging, local SQLite memory over MCP, and composable engineering skills like dev-lifecycle and verify. | View Project → |
| magpie | ★ 1.6K | AI Coding | Go | coding agents · model routing · LLM gateway · model management · provider management · OpenAI-compatible · Anthropic API · CLI · menu bar · profiles | Magpie is a desktop, terminal, and CLI tool for managing models across coding agents such as Claude Code, Codex, and Gemini CLI. Its local gateway exposes configured providers and signed-in subscriptions through compatible APIs, with shared catalogs and routing groups. | View Project → |
| ClaudeCode-Portable | ★ 1.5K | AI Coding | JavaScript | claude-code · portable · usb-drive · ai-coding-agent · multi-provider · no-install · browser-dashboard · local-models · ollama · lm-studio · openrouter · offline-inference · provider-switching · agent-sdk · cross-platform · terminal-interface | Portable AI coding workspace bundling the official Claude Code CLI and Agent SDK with a browser dashboard. Runs from a USB drive on Windows/Linux/macOS and connects to Anthropic, OpenAI, Gemini, OpenRouter, NVIDIA NIM, Ollama, and LM Studio. | View Project → |
| rulesync | ★ 1.5K | AI Coding | TypeScript | cli · ai-rules · config-management · mcp · skills · subagents · agent-hooks · claude-code · cursor · github-copilot · codex-cli · agents-md · multi-tool-sync · typescript · nodejs | Node.js CLI that manages a single .rulesync source of truth and generates or imports config files (rules, MCP, commands, subagents, skills, hooks, permissions) for 40+ AI coding tools such as Claude Code, Cursor, Copilot and Codex CLI. | View Project → |
| agor | ★ 1.4K | AI Coding | TypeScript | coding agents · multi-agent · agent orchestration · git worktrees · MCP · team collaboration · self-hosted · agent sessions · AI teammates · developer tools | A self-hosted collaborative workspace for running coding agents such as Claude Code, Codex, and Gemini CLI on isolated Git branches. It provides agent sessions, a shared board, persistent AI teammates, and an MCP interface agents can use to manage work. | View Project → |
| haft | ★ 1.4K | AI Coding | Go | AI coding agents · project memory · engineering decisions · MCP · agent skills · evidence tracking · decision staleness · spec-driven development · local-first | Haft adds local project memory and engineering-decision governance to coding agents. It provides MCP integrations and skills for framing problems, comparing options, recording decisions, and checking evidence or specifications for staleness. | View Project → |
| Wake | ★ 1.3K | AI Coding | Rust | coding agents · session manager · conversation search · transcript viewer · session resume · MCP server · local-first · multi-agent | A native desktop app for browsing, searching, and resuming coding-agent sessions across tools such as Claude Code, Codex, Cursor, and OpenCode. Includes a read-only MCP server and CLI for accessing indexed session history. | View Project → |
| ai-setup | ★ 1.3K | AI Coding | TypeScript | claude-code · cursor · codex · agent-skills · mcp · context-management · cli · developer-tools · ai-agents · github-copilot · opencode · agents-md · cursorrules · config-sync · compaction · typescript | Caliber is a CLI that keeps AI coding agent context in sync: it generates and refreshes CLAUDE.md, Cursor rules, AGENTS.md and Copilot instructions, mirrors skills/MCP config across Claude Code, Cursor, Codex, OpenCode and Copilot, scores config quality, and offers lossless transcript compaction. | View Project → |
| whiteboard | ★ 1.3K | AI Coding | TypeScript | AI coding agents · code review · software design · desktop app · semantic diff · agent workspace · diagrams · decision logs | A desktop workspace for humans and coding agents to review code changes and collaborate on software design. Agents can draw diagrams, present semantic diffs, and record decisions linked to code. | View Project → |
| jevgrep | ★ 1.2K | AI Coding | TypeScript | coding agents · code search · semantic search · context retrieval · CLI · repository exploration · agent skill · SWE-bench | A CLI that helps coding agents find relevant files and source context by asking repository questions. It uses Jev to rank folders, files, and declarations, then returns evidence for the agent to use. | View Project → |
| openharness | ★ 1K | AI Coding | Dart | coding agents · agent harness · multi-agent · terminal · tmux · remote development · worktrees · encrypted connections · local models · domain-specific harnesses | A desktop app and CLI for running and managing coding-agent sessions across machines. It integrates existing agent CLIs in tmux, supports swarms and Git worktrees, and provides domain-specific harnesses with tools and live viewers. | View Project → |
| gentle-shell | ★ 959 | AI Coding | TypeScript | ai-coding-agent · agent-harness · subagents · spec-driven-development · openspec · tdd · code-review · agent-skills · orchestration · developer-tools · mcp · llm · pi-coding-agent · typescript · workflow-guardrails · cli | gentle-shell turns Pi into an opinionated coding-agent workspace: orchestrator plus focused subagents, ODD/SDD-OpenSpec workflows, strict TDD evidence, native change review, and skill discovery. Built for developers who want inspectable, human-led agent workflows in TypeScript. | View Project → |
| agent-deck | ★ 948 | AI Coding | Go | tui · terminal · session-manager · tmux · claude-code · codex · gemini-cli · opencode · mcp · skills · multi-agent · cli · git-worktrees · cost-tracking · golang · developer-tools | Go TUI that acts as mission control for AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode). One terminal shows every session, with fork, groups, MCP/skill managers, git worktrees, cost tracking, and remote control via a conductor bot. | View Project → |
| repoprompt-ce | ★ 937 | AI Coding | Swift | context-engineering · coding-agents · mcp · mcp-server · agent-orchestration · prompt-engineering · macos · swift · codebase-context · cli-agents · git-diff · codemaps · developer-tools · worktrees · multi-root-workspace · agent-harness | RepoPrompt CE is a free native macOS app that engineers reviewable context for AI coding agents from files, CodeMaps, repo structure and Git diffs, with a bundled MCP server and CLI so external agents can search repos and run agent sessions. | View Project → |
| Citadel | ★ 923 | AI Coding | JavaScript | claude-code · openai-codex · agent-orchestration · mcp · project-memory · hooks · plugin · multi-agent · developer-tools · parallel-agents · cost-telemetry · safety-hooks · worktrees · evidence · cli · github-actions | Citadel is a plugin operating layer for Claude Code and OpenAI Codex that adds a single /do entry point, repo-local persistent memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets in isolated worktrees, with evidence-based verification states (passed/failed/blocked/unknown). | View Project → |
| codexia | ★ 918 | AI Coding | TypeScript | AI coding agents · agent workstation · Codex CLI · Claude Code · ACP · task scheduler · Git worktrees · remote control · MCP marketplace · agent skills | A desktop and headless workstation for Codex CLI, Claude Code, and ACP-compatible agents. It combines agent sessions with task scheduling, Git worktree management, remote control, and MCP and skills marketplaces. | View Project → |
| Ix | ★ 910 | AI Coding | TypeScript | codebase-understanding · code-analysis · persistent-memory · system-graph · code-mapping · MCP · CLI · coding-agents · program-analysis | Ix maps repositories into a persistent graph of symbols, calls, imports, and relationships. Its CLI and MCP server let developers and coding agents query architecture, trace flows, and assess change impact across sessions. | View Project → |
| dscode | ★ 864 | AI Coding | JavaScript | coding-agent · terminal · cli · tui · deepseek · multi-agent · subagents · mcp · session-management · code-review · memory · macos · developer-tools · agentic · non-interactive · sandbox | DSCODE is a macOS terminal coding agent harness built on DeepSeek Harness: a persistent shell writes code and runs tests, and sessions see each other so agents can hand off tasks, review diffs and share memory. Ships a TUI, CLI, Chrome MCP, subagents and independent auto-review. | View Project → |
| VTCode | ★ 851 | AI Coding | Rust | terminal · tui · rust · coding-agent · cli · mcp · agent-skills · agent-plugins · acp · sandboxing · evals · multi-provider · session-resume · autonomous · code-review | VT Code is a Rust terminal coding agent: one static binary with a keyboard-first TUI, headless exec, sandboxed tool execution, durable sessions, built-in evals, and MCP, Agent Skills, Plugin, and ACP extensibility across OpenAI, Anthropic, Gemini, and local models. | View Project → |
| storybloq | ★ 755 | AI Coding | TypeScript | Claude Code · Codex · coding-agent workflows · session continuity · project memory · handover · MCP server · agent skill · CLI · workflow management | Storybloq gives Claude Code and Codex a Git-backed project memory and workflow system, storing stories, plans, lessons, and handovers in a `.story/` directory. It includes a CLI, MCP server, agent skills, and an optional Mac app. | View Project → |
| Locus | ★ 743 | AI Coding | Rust | unity · gamedev · ai-agent · coding-agent · hot-reload · csharp · rust · tauri · vue · roslyn · static-analysis · debugging · version-control · editor-ui · desktop-app · llm | Open source AI dev agent for Unity that writes C#, edits scenes and assets, and hot-reloads changes without domain reload while preserving Play Mode. Built in Rust/Tauri with Vue frontend, Roslyn semantic analysis, runtime debugging and visual version control for YAML assets. | View Project → |
| horizon | ★ 710 | AI Coding | Rust | terminal-emulator · infinite-canvas · ai-agents · coding-agents · mcp · browser-automation · workspace-manager · terminal-multiplexer · session-persistence · git-integration · rust · egui · wgpu · cross-platform · agent-usage-tracking · desktop-app | Horizon is a Rust desktop app that places terminals, coding-agent TUIs (Claude Code, Codex, Gemini, Grok), live browsers and git panels on an infinite canvas grouped into workspaces. It ships an MCP browser-automation server agents can share, plus session persistence and token-usage tracking. | View Project → |
| jev-review | ★ 641 | AI Coding | TypeScript | code-review · ai-code-review · cli · local-dashboard · typescript · diff-review · codebase-scan · structured-output · llm-workflow · severity-scoring · test-coverage · security-review · nodejs · static-analysis | CLI and local dashboard that runs staged LLM code reviews over a Git diff or a full codebase using TypeSafe Jev, scoring correctness, security, reliability and test gaps. Orchestration and thresholds live in code; findings are review prompts, not proof of defects. | View Project → |
| sigmap | ★ 637 | AI Coding | JavaScript | code-context · code-grounding · AI coding · MCP server · hallucination detection · code intelligence · token reduction · offline · deterministic · CLI · code signatures | SigMap builds a deterministic, offline map of repository files and symbols for AI coding assistants. Its CLI and MCP server support code search, compact context generation, and verification of AI answers against real code. | View Project → |
| casbin-gateway | ★ 637 | AI Coding | Go | AI coding agents · LLM gateway · API proxy · agent monitoring · access control · model routing · usage tracking · prompt logging · API authenticity | A Go gateway for AI coding agents that routes requests to 44 model vendors through one endpoint. It monitors agent activity, grades API authenticity, enforces per-agent permissions, and records prompts and usage. | View Project → |
| agentty | ★ 614 | AI Coding | C++ | terminal · cli · tui · coding-agent · pair-programming · static-binary · rag · mcp · sandbox · multi-provider · local-first · graphrag · hybrid-search · acp · cpp · byok | agentty is an MIT-licensed terminal coding agent written in C++26, shipped as one ~17MB static binary with millisecond startup and no Node/Python runtime. It supports many providers (Anthropic, OpenAI, Groq, Gemini, Ollama, OpenRouter, etc.), sandboxes shell commands, and ships a fully local hybrid BM25 + embedding Gra | View Project → |
| claude-token-optimizer | ★ 600 | AI Coding | JavaScript | Claude Code · token optimization · context management · CLI · documentation · hooks · developer tools | A JavaScript CLI for reducing Claude Code context usage by organizing project documentation, measuring token costs, and pruning or compressing CLAUDE.md. Includes hooks for token monitoring and selectively loading relevant project knowledge. | View Project → |