Vibe Coding DiscoverCategory
AI Coding
Coding agents, IDE assistants, and software engineering automations.
| Project name | Stars | Category | Language | Tags | Summary | View Project |
|---|---|---|---|---|---|---|
| claw-orchestrator | ★ 580 | AI Coding | TypeScript | claude-code · codex · cursor-agent · opencode · antigravity · grok · multi-agent · orchestration · persistent-sessions · mcp-server · acp · openai-compatible · agent-council · autoloop · cli · typescript | Claw Orchestrator wraps Claude Code, Codex, Antigravity, Grok, OpenCode or custom CLIs as persistent programmable sessions and adds multi-agent councils, autoloop Planner/Coder/Reviewer runs, MCP/ACP servers, and an OpenAI-compatible endpoint. A TypeScript runtime for orchestrating coding agents from CLI or any editor. | View Project → |
| avibe | ★ 569 | AI Coding | Python | coding-agents · local-first · agent-os · chatops · browser-workbench · Claude Code · Codex · OpenCode · Slack · Discord · Telegram · WeChat · Lark | A local-first workbench and chat interface for running Claude Code, Codex, and OpenCode on your own machine. Connect through a browser or messaging apps to start, steer, and monitor coding-agent sessions remotely. | View Project → |
| smart-ralph | ★ 549 | AI Coding | Shell | claude-code · claude-code-plugin · spec-driven-development · agentic-coding · coding-agent · ralph-loop · workflow-automation · autonomous-coding · codex · developer-tools · agent-skills · task-orchestration · codebase-indexing · claude-skills · spec-kit · hooks | Claude Code and Codex plugin that runs the Ralph loop on top of a structured spec workflow: research, requirements, design, and tasks are written to disk, then executed task-by-task with fresh context and resumable state. | View Project → |
| nanocodex | ★ 518 | AI Coding | Rust | rust · openai · codex · coding-agent · sdk · embeddable-agent · cli · tui · mcp · computer-use · sandbox · subagents · voice · wasm · python-bindings · nodejs | Nanocodex is a Rust library-first SDK that embeds OpenAI's Responses agent loop end-to-end: retained sessions, typed history, tools, Code Mode, branches, retries and cleanup. Node, Python, WASM and native CLI/desktop consumers prove the same contract, so you keep your own UI, memory and infrastructure. | View Project → |
| sandboxed.sh | ★ 513 | AI Coding | Rust | AI coding agents · agent orchestration · sandboxing · workspace isolation · MCP · self-hosted · mission execution · Claude Code · OpenCode · Codex · skills · web3 | Self-hosted backend for dispatching and monitoring AI coding-agent missions in isolated Linux workspaces. Supports Claude Code, OpenCode, Codex, Gemini, and Grok runtimes, with MCP control, project tracking, and a web dashboard. | View Project → |
| agent-manager | ★ 496 | AI Coding | Go | AI coding agents · terminal UI · tmux · agent management · session management · diff review · git worktrees · MCP · Go | A Go terminal UI for managing multiple AI coding agent CLIs in persistent tmux sessions. Track live status, send prompts, create worktrees, and review diffs with comments that return to the agent. | View Project → |
| amux | ★ 496 | AI Coding | Rust | coding agents · multi-agent orchestration · agent control plane · parallel workers · task board · self-hosted · model switching · scheduling · tmux | A self-hosted Rust control plane for coordinating parallel AI coding agents from a web dashboard or phone. It provides shared tasks, worker messaging, schedules, model switching, and session recovery for Claude Code, Codex, Gemini CLI, OpenCode, and Ollama. | View Project → |
| claudexor | ★ 478 | AI Coding | TypeScript | coding-agents · multi-harness · agent-orchestration · claude-code · codex-cli · cursor-cli · opencode · quota-management · multi-account · cross-model-review · best-of-n · local-first · mcp-server · cli · code-review · macos | Local-first control plane that runs Codex CLI, Claude Code, Cursor CLI and OpenCode behind one typed interface, with quota-aware multi-account rotation, best-of-N races, cross-model review and auditable cost/evidence receipts. CLI + daemon, macOS app, MCP server. | View Project → |
| opencode-swarm | ★ 478 | AI Coding | TypeScript | multi-agent · agent-swarm · opencode-plugin · orchestration · code-review · qa-gates · guardrails · coding-agent · planning · testing · cli · typescript · bun · automation · sast · mcp | OpenCode plugin that turns one AI coding session into an architect-led agent swarm: specialized planning, coding, review, test, and docs roles with gated pipelines, scope enforcement, shell-write guardrails, and resumable .swarm state. | View Project → |
| coco | ★ 471 | AI Coding | HTML | AI coding · agent orchestration · agent skills · slash commands · persistent state · multi-agent workflows · developer tools · local-first · verification gates · prompt engineering | CoCo adds agent orchestration, 226 skills, 386 commands, specialized agents, and persistent project state to Claude Code, Cursor, and Codex. It provides workflow structure and prompts; execution runs through the host coding assistant. | View Project → |
| late-cli | ★ 433 | AI Coding | Go | coding-agent · multi-agent · long-horizon · local-LLM · subagents · context-management · MCP · skills · sandboxing · CLI | Late is a Go CLI coding agent that assigns planning and verification to an orchestrator while isolated coder and researcher subagents handle execution. Its context-isolation design supports long workflows, local or cloud models, MCP, plugins, and sandboxed runs. | View Project → |
| agnix | ★ 426 | AI Coding | Rust | linter · lsp · ai-coding-assistant · agent-config · claude-code · mcp · skills · rust · cli · vscode-extension · autofix · static-analysis · codex · cursor · copilot · devtools | Rust-based linter and language server that validates AI coding assistant configs: CLAUDE.md, AGENTS.md, SKILL.md, hooks, plugins and MCP files. Ships 456 rules with autofixes, a CLI, GitHub Action and LSP plugins for VS Code, JetBrains, Neovim and Zed. | View Project → |
| awesome-opus5-5-videos | ★ 381 | AI Coding | — | prompt collection · creative coding · AI-generated animation · motion graphics · Three.js · Claude | A collection of 282 Claude Opus 5.5 prompts for generating coded videos and animations, with examples spanning motion graphics, explainers, 3D scenes, and interactive projects. Each entry links to the original post. | View Project → |
| notebook-intelligence | ★ 346 | AI Coding | Python | jupyterlab · jupyter · notebook · ai-coding-assistant · inline-completion · chat-ui · mcp · agent-skills · claude-code · copilot · ollama · plugins · rulesets · code-generation · local-llm · notebook-agent | Notebook Intelligence is a JupyterLab extension adding an AI coding assistant: chat, inline code generation, auto-complete, and a notebook agent. Backed by GitHub Copilot, Ollama, Claude Code CLI, or OpenAI/LiteLLM-compatible endpoints, with MCP, skills, plugins, and rulesets. | View Project → |
| swival | ★ 342 | AI Coding | Python | cli · coding-agent · open-models · local-llm · mcp · a2a · acp · code-review · security-audit · context-management · skills · sandboxing · secrets-encryption · tool-calling · python-api · offline | Swival is a Python CLI coding agent designed to work equally well with open/local models and hosted APIs. It adds context management, resumable goal-driven sessions, review and security-audit passes, secret filtering, plus MCP/A2A/ACP integration and a Python API. | View Project → |
| genie | ★ 338 | AI Coding | TypeScript | ai-agents · coding-agents · cli · orchestration · parallel-agents · worktrees · code-review · skills · claude-code · anthropic · automation · developer-tools · context-engineering · vibe-coding · terminal · task-management | Genie is a TypeScript CLI planning-and-execution layer for AI coding agents: it interviews you into a plan, dispatches parallel agents in isolated git worktrees, and reviews the resulting code before you merge. State lives in git markdown plus a local SQLite file, not a daemon. | View Project → |
| Calyx | ★ 328 | AI Coding | Swift | coding-agents · agent-orchestration · macOS · terminal · parallel-agents · approval-inbox · MCP · session-management · code-review · browser-automation | A native macOS terminal for running and supervising coding agents such as Claude Code, Codex, and OpenCode in parallel. It adds shared approvals, session management, diff review, browser automation, and MCP tools while retaining a terminal workflow. | View Project → |
| agentglass | ★ 328 | AI Coding | TypeScript | agent-observability · cost-tracking · token-usage · claude-code · codex · gemini-cli · opencode · permission-gate · tmux · local-first · sqlite · electron · android-companion · session-monitoring · dashboard · llm-observability | Local-first cockpit that attaches to already-running AI coding agents (Claude Code, Codex, Gemini CLI, OpenCode) and shows live cost, tokens, tool calls and blocked permission gates on desktop or phone. Includes diff/PR review, tmux terminals and gated dangerous commands. | View Project → |
| jev-router | ★ 328 | AI Coding | JavaScript | model-routing · claude-code · codex · cost-optimization · llm-router · proxy · cli · nodejs · prompt-routing · fail-open · statusline · typesafe | jev-router wraps Claude Code and OpenAI Codex with a loopback proxy that scores each fresh user turn and routes it to the cheapest sufficient model tier. It preserves native CLI auth, tools and sessions, and is fail-open with a bundled explain skill. | View Project → |
| no_human | ★ 319 | AI Coding | Python | coding-agent · agent-orchestration · ai-code-review · pull-requests · claude-agent-sdk · mcp · developer-tools · sdlc-automation · harness-engineering · verification · git-worktrees · self-hosted · adversarial-review · ticket-to-pr · cli · desktop-app | Self-hosted Python orchestrator that drives the Claude Agent SDK from a ticket to a review-passed pull request, adding an independent reviewer model, tamper detection, reproduction gating, and honest stops when blocked. | View Project → |
| JevRev | ★ 305 | AI Coding | TypeScript | AI coding workflows · agent orchestration · decision support · evidence-based evaluation · CLI · workflow monitoring · local LLMs | A TypeScript CLI that supports coding agents with approach selection, evidence-based iteration, and read-only session monitoring. It works alongside tools such as Codex or Claude Code and supports hosted, local, or replayed decision providers. | View Project → |
| ultimate_bug_scanner | ★ 303 | AI Coding | Python | AI coding agents · static analysis · bug detection · code quality · security analysis · CLI · pre-commit · CI · multi-language · SARIF · agent guardrails | A multi-language static analyzer that detects bug patterns and security issues, with JSON/SARIF output and integrations for AI coding agent guardrails. Supports scans of repositories, staged files, and diffs, plus CI failure thresholds and baseline comparisons. | View Project → |
| aft | ★ 303 | AI Coding | Rust | coding-agents · code-search · semantic-search · tree-sitter · symbol-aware-editing · grep · glob · lsp · code-health · pty · background-tasks · output-compression · opencode · pi · rust · plugin | Rust binary plus OpenCode/Pi adapters that give coding agents an IDE-like sensorimotor layer: tree-sitter symbol outlines, semantic and trigram search, call graphs, code-health reports, symbol-aware edits, bash output compression, background tasks and PTY sessions. Hoists host read/edit/bash/grep tools to cut token use | View Project → |
| pi-bluebook | ★ 283 | AI Coding | Markdown | chinese · tutorial · learning-path · coding-agent · agent-harness · agent-skills · context-engineering · subagents · session-management · extensions · vitepress · documentation · prompt-caching · long-running-agents · beginner-guide · zh-tw | A Chinese-language learning bluebook for Pi Coding Agent, a minimal terminal coding harness. It walks beginners from install and login to sessions, context compaction, skills, extensions, subagents and long-running agent workflows, with verifiable exercises. | View Project → |
| monet | ★ 279 | AI Coding | Rust | coding-agents · claude-code · codex · session-manager · desktop-app · tauri · mcp-server · multi-agent · parallel-sessions · session-search · scheduled-tasks · token-usage · macos · windows · local-first · byoai | Monet is a Tauri desktop mission-control app for coding agents: it indexes Claude Code and Codex session history read-only, lets you search it, and drives many agent sessions in parallel with live status, permission approvals, model hot-switching, scheduled routines and a built-in MCP server. Local-first, zero telemetr | View Project → |
| jev-codex-router | ★ 277 | AI Coding | JavaScript | model-routing · codex · cost-optimization · reasoning-effort · llm-router · proxy · macos · python · openai-responses · sse-streaming · launchd · fail-open · backtest · shadow-mode · local-first · typesafe | Local server that plugs into Codex Router as a generic provider and classifies every turn with Jev to pick model, reasoning effort and speed tier. Reports ~60% savings vs an all-frontier baseline, with fail-open, kill switch, shadow mode and a dry-tandem fallback. | View Project → |
| aghub | ★ 272 | AI Coding | TypeScript | mcp · ai-agents · claude-code · cursor · windsurf · gemini-cli · opencode · configuration-management · skills · plugin-manager · cli · tauri · cross-platform · developer-tools · mcp-marketplace · assistant-hub | aghub is a cross-platform Tauri desktop app and CLI that centralizes configuration for 22+ AI coding agents. It manages MCP servers, portable skills, Claude Code plugins, and custom model endpoints from a single hub with per-agent and per-project scoping. | View Project → |
| cezar | ★ 252 | AI Coding | TypeScript | coding agents · multi-agent · parallel coding · agent orchestration · Git worktrees · self-hosted · autonomous agents · workflows · Claude Code · Codex · OpenCode | A self-hostable control center for running Claude Code, Codex, OpenCode, and other coding agents in parallel. Tasks run in separate Git worktrees and can follow workflows with checks, retries, and live progress review. | View Project → |
| Astra-Ares | ★ 246 | AI Coding | JavaScript | adaptive-reasoning · reasoning-effort · token-optimization · codex-cli · cli · prompt-caching · llm-routing · agent-harness · cost-reduction · patched-cli · nodejs · openrouter · experimental | Astra-Ares is an experimental patched Codex CLI that lets an LLM evaluator (Jev) pick GPT-6 reasoning effort per generation, aiming to cut token usage while preserving prompt-cache prefixes. Requires Node 22+, Rust, and a ~10GB local Codex build. | View Project → |
| peri | ★ 215 | AI Coding | Rust | rust · coding-agent · tui · claude-code-compatible · acp · mcp · multi-agent · streaming-markdown · workflow · artifacts · web-search · headless · web-pty · langfuse · skills · lightweight | Peri is a lightweight Rust coding agent (~50MB RAM) with a TUI, headless mode, ACP and MCP support. It runs Claude Code-style plugins, skills, workflows, parallel agents, web search, and Langfuse tracing on top of Anthropic or OpenAI-compatible endpoints. | View Project → |
| pi-desktop | ★ 210 | AI Coding | TypeScript | coding-agent · desktop-gui · electron · ide · ai-coding-assistant · diff-review · terminal · code-editor · multi-agent · permissions · themes · i18n · alpha · developer-tools · git-worktree · session-management | Electron desktop GUI for the Pi and oh-my-pi coding agents, combining streaming chat, file tree, CodeMirror editor, terminal, and a diff-review rail with commit/push/PR actions. Adds permission rules, multi-workspace sessions, and optional Claude/Codex council planning. Alpha. | View Project → |
| procoder | ★ 209 | AI Coding | Go | ai-coding · code-quality · commit-gate · linter · static-analysis · code-review · claude-code · agent-hooks · security · mcp · spec-driven · tdd · developer-tools · go · self-learning · git-hygiene | Procoder is a single Go binary that gives AI coding agents a non-negotiable commit gate, refusing quality controllers for spec/plan/test/release steps, and a lessons loop that closes escaped bug classes. No runtime deps; adapters for 20+ agents. | View Project → |
| story-ui | ★ 205 | AI Coding | TypeScript | Storybook · code generation · AI coding · design systems · component libraries · MCP · browser verification · TypeScript | Story UI adds an AI-powered workspace to Storybook that generates repository-ready stories using components discovered in your project. It supports multiple LLM providers and checks generated screens in a real browser. | View Project → |
| unica | ★ 201 | AI Coding | Rust | 1C:Enterprise · Codex plugin · Claude Code plugin · MCP server · agent skills · BSL · metadata generation · form development · code search | A Codex and Claude Code plugin for 1C:Enterprise development. It provides agent skills and an MCP server for creating and validating metadata, building forms and reports, searching BSL code, and running 1C operations. | View Project → |
| martin-loop | ★ 190 | AI Coding | TypeScript | ai-coding-agents · agent-governance · budget-enforcement · mcp · claude-code · codex · rollback · audit-trail · policy-as-code · observability · llmops · control-plane · verification · receipts · github-actions · cli | MartinLoop is a governed runtime and CLI for AI coding agents. It adds budgets, iteration caps, edit scope, verifier checks, rollback evidence, and run receipts across Codex, Claude Code, and MCP hosts. | View Project → |
| pi-go | ★ 181 | AI Coding | Go | coding-agent · terminal · tui · cli · multi-provider · mcp · lsp · subagents · skills · sandboxed-tools · session-persistence · memory · git-tools · go · rpc-server · security-audit | pi-go is a Go terminal coding agent built on Google ADK Go: multi-provider LLM routing, sandboxed read/write/shell/git tools, LSP, subagents, MCP/skills extensions, session persistence, and a 4-layer SQLite memory palace. MIT-licensed, TUI plus print/JSON/RPC modes. | View Project → |
| blade-code | ★ 179 | AI Coding | TypeScript | cli · coding-agent · terminal · mcp · multi-model · agent-tools · browser-automation · subagents · skills · headless · memory · permission-modes · plugin-system · vscode · typescript · task-board | Blade Code is a TypeScript CLI/Web/headless AI coding agent with 20+ built-in file, search, shell, git and browser tools, MCP and Skills extensibility, subagent orchestration, persistent memory, and unified access to 38+ LLM providers via pi-ai. | View Project → |
| pi-automode | ★ 179 | AI Coding | TypeScript | auto-mode · guardrails · permissions · coding-agent · pi · pi-extension · omp-plugin · safety · classifier · hard-deny · bash-analysis · hooks · observability · typescript · llm · tool-call-filtering | Pi/Oh My Pi extension that adds Claude Code-style auto mode: it intercepts agent tool calls and blocks them via permission rules, deterministic hard-deny checks, or an LLM classifier. Includes slash commands, a status line, and read-only diagnostics. Not a sandbox. | View Project → |
| AiCode | ★ 177 | AI Coding | Kotlin | android · kotlin · ai-agent · mcp · code-editor · terminal · alpine-linux · termux · subagents · git-integration · ssh · proot · jetpack-compose · on-device · multi-provider | AiCode is an Android app that turns a phone into an AI coding workstation: a multi-provider AI agent with file, shell and search tools, an embedded Alpine Linux/PRoot terminal, code editor, Git UI, MCP support and parallel subagents, plus optional remote SSH execution. | View Project → |
| agentbox-sdk | ★ 163 | AI Coding | TypeScript | coding agents · sandboxing · TypeScript SDK · agent orchestration · streaming · multi-provider · MCP · sub-agents | A TypeScript SDK for running Claude Code, OpenCode, and Codex as interactive server processes inside local or cloud sandboxes. It provides a unified API for sandbox providers, streaming events, approvals, and background work. | View Project → |
| evener | ★ 159 | AI Coding | Go | coding-agent · cli · go · agent-loop · tool-calling · multi-provider · mcp · subagents · skills · plugins · hooks · sandboxing · web-ui · tui · session-forking · background-jobs | Evener is a Go coding agent that loops over read, write, run and search tools using native LLM tool-calling across OpenAI, Anthropic, Google and many other providers. It ships a hub web UI for concurrent sessions, a TUI, MCP support, subagents, skills, plugins and a non-interactive CLI for CI. | View Project → |
| token-saver | ★ 152 | AI Coding | Python | token-optimization · context-window · claude-code · cli-compression · llm-cost-optimization · context-engineering · agentic-ai · developer-tools · hooks · python · deterministic-compression · ci-agents | Local, deterministic CLI-output compressor that sits between your terminal and AI coding assistants, using 36 format-aware processors to cut tool output tokens by 60-99% while preserving errors, diffs and stack traces. Installs as a Claude Code / Antigravity plugin; no network calls or extra model inference. | View Project → |
| codex-claude-code-config | ★ 150 | AI Coding | Python | claude-code · codex · agent-harness · hooks · skills · multi-agent · context-management · prompt-engineering · guardrails · agent-security · workflow-patterns · agents-md · configuration-kit · mcp · coding-agents · dev-workflow | A configuration system for Claude Code, Codex, and other coding agents: architectural principles, Python enforcement hooks, installable skills, and rules for multi-agent orchestration, context handoff, and agent security. Drop-in kits for global or project-local install. | View Project → |
| omk | ★ 144 | AI Coding | TypeScript | coding-agent · terminal · multi-agent · agent-runtime · orchestration · evidence-gates · workflow-automation · code-review · local-first · MCP · model-routing · session-replay | OMK is a TypeScript terminal coding-agent CLI with support for multiple model providers, tools, and resumable sessions. Optional workflows add multi-agent DAG routing and evidence-gated verification; ordinary prompts use a single agent loop. | View Project → |
| octomind | ★ 143 | AI Coding | Rust | ai-coding-agent · agent-runtime · mcp-native · cli · rust · daemon · ci-cd · guardrails · skills · acp · websocket · multi-provider · autonomous-agents · developer-tools · sessions · cost-control | Rust AI coding agent runtime: one binary, any model, MCP-native. Runs interactively, piped in CI, as a daemon, over WebSocket, or as an ACP sub-agent, with TOML-configured roles, guardrails, skills, and cost budgets instead of framework code. | View Project → |
| claude-code-studio | ★ 139 | AI Coding | JavaScript | Claude Code · coding assistant · multi-agent · task orchestration · Kanban · scheduling · MCP · skills · web interface · remote access | A web and desktop workspace for Claude Code CLI with real-time chat, scheduled tasks, Kanban, multi-agent orchestration, MCP servers, and remote access through SSH or Telegram. | View Project → |
| txcript | ★ 137 | AI Coding | Rust | coding agents · session transcripts · transcript conversion · Claude Code · Codex · OpenCode · Cursor · CLI · MCP · Rust · WebAssembly | Rust library, CLI, and WebAssembly package for converting, searching, and editing coding-agent transcripts across tools such as Claude Code, Codex, OpenCode, and Cursor. Includes read-only MCP tools for finding and reading past sessions. | View Project → |
| my-pi | ★ 132 | AI Coding | TypeScript | coding-agent · cli · mcp · lsp · evals · telemetry · sqlite · prompt-presets · skills · team-mode · guardrails · observability · redaction · tui · typescript · pi-package | my-pi is a curated, composable Pi coding-agent CLI distribution wiring MCP servers, LSP tools, skills, prompt presets, guardrails, redaction, local SQLite evals/telemetry, and team mode, plus installable per-feature @spences10/pi-* packages. | View Project → |
| postal | ★ 129 | AI Coding | Python | coding-agent · terminal · tui · cli · openrouter · sub-agents · mcp · sessions · approval-policy · skills · tool-use · python · rich · context-compaction · code-editing · shell-execution | Postal is an open-source Python terminal AI coding agent that plans, edits, runs and reviews code using any model via OpenRouter. It offers a full-screen TUI, built-in file/bash/web/MCP tools, specialized sub-agents, approval policies, and checkpointed resumable sessions. | View Project → |
| token-goat | ★ 126 | AI Coding | TypeScript | token-optimization · context-window · AI coding agents · CLI · hooks · prompt-injection protection · file interception · output filtering · image compression · session compaction · skills caching · MCP · cross-platform | A TypeScript CLI and hook layer for AI coding agents that reduces context usage by intercepting repeated reads, filtering command output, compacting images and documents, and preserving session context. Supports multiple coding-agent CLIs and includes prompt-injection protections. | View Project → |
| clawd-conduit | ★ 120 | AI Coding | Shell | claude-code · hooks · desktop-pet · macos · developer-tools · permission-prompts · notifications · ai-agents · dotfiles · shell · installer · lifecycle-events · clawd-on-desk | Shell-based wiring layer that forwards all 15 Claude Code lifecycle hook events to the Clawd on Desk desktop pet, including blocking permission requests you can allow/deny from the desktop. Ships idempotent macOS install/uninstall scripts that safely merge into ~/.claude/settings.json. | View Project → |
| claude-telegram-supercharged | ★ 115 | AI Coding | TypeScript | Claude Code · Telegram · AI coding agent · MCP server · voice messages · agentic mode · daemon · conversation memory · model routing · self-hosted | Extends the official Claude Code Telegram plugin with voice messaging, live tool-call updates, persistent conversation memory, model routing, and a self-restarting daemon for remote, always-on access to Claude Code. | View Project → |
| pi-ling | ★ 106 | AI Coding | TypeScript | coding-agent · agent-runtime · electron · desktop-app · skills · subagents · session-event-log · sqlite · approval-policy · diff-view · terminal · agent-eval · multi-provider · typescript · audit-trail · workbench | pi-ling is an Electron desktop workbench for coding agents that runs Native, DSH and Codex runtimes in one session. Every tool call, file edit and model output lands in a SQLite event log, with effect-based approval policies, file-based skills, subagents and a coding eval toolchain. | View Project → |
| tasktrooper | ★ 105 | AI Coding | Go | coding-agents · multi-agent · agent-orchestration · local-first · kanban · autonomous-workflows · Claude Code · Cursor · OpenCode · MCP · code-review · software-delivery | A local-first platform that dispatches software tasks from a Kanban board to role-based agents running through Claude Code, Cursor, Antigravity, OpenCode, or model APIs. Coordinates implementation, review, QA, and release workflows on your machine. | View Project → |
| claude-plugins | ★ 102 | AI Coding | Python | Claude Code · multi-agent · software delivery · implementation planning · code generation · code review · LLM-as-judge · self-learning · GitHub PRs · SDLC | A suite of Claude Code plugins for multi-agent software delivery, covering project setup, implementation planning and coding, automated PR reviews, quality judging, and organizational learning. Includes workflow gates grounded in the codebase. | View Project → |
| Benzi | ★ 100 | AI Coding | Python | AI coding agent · code intelligence · code indexing · tree-sitter · MCP · call graph · data flow · symbol resolution · runtime tracing · automated code editing · incremental indexing | Compiler-backed code intelligence infrastructure for AI coding agents. It builds a tree-sitter index with resolved symbols, call relationships, and data flow, then exposes structured query, edit, test, and rollback tools, including MCP compatibility. | View Project → |
| tuweb.dev | ★ 100 | AI Coding | Astro | autonomous coding · AI code generation · Claude Code · human voting · automated deployment · rollback · prompt security | A community-driven website where visitors vote on feature ideas and Claude Code implements the winning proposal every 30 minutes. The project includes prompt moderation, diff restrictions, build checks, deployment verification, and automatic rollback. | View Project → |
| winnow | ★ 100 | AI Coding | Python | claude-code · claude-code-plugin · context-management · hooks · token-reduction · context-pruning · llm-agents · relevance-judge · calibrated-model · mcp · python · shadow-mode | A Claude Code plugin that judges each large tool result with a calibrated System One model (Jev, or a Haiku adapter) and replaces unneeded blocks with a stub plus a recall key. Hooks, shadow mode, and MCP server included; local cache keeps the hidden text restorable. | View Project → |
| Canny | ★ 85 | AI Coding | TypeScript | coding-agent-guardrails · agent-hooks · evidence-ledger · done-gate · deterministic-checks · secret-detection · Claude Code · Codex CLI | A TypeScript supervision layer for Claude Code and Codex CLI. Hooks record agent actions and block completion when code changes lack a passing check; deterministic rules can also catch secrets and test removal. Jev-backed judgments are advisory. | View Project → |
| opencode-agents | ★ 12 | AI Coding | TypeScript | opencode · ai-agents · coding-agent · prompts · agent-config · multi-agent · subagents · plan-first · workflow · cli · typescript · code-review · automated-testing · evals · system-builder · installer | OpenCode agent framework: installable prompts, agents, subagents and commands for plan-first, approval-based coding workflows, plus an eval harness that runs agent test suites against Claude, GPT-4 and Grok. Built for the OpenCode CLI, not standalone. | View Project → |