Explore

Local-first AI memory system that stores conversation and project history verbatim and retrieves it via pluggable vector backends (ChromaDB default, plus Milvus/Qdrant/pgvector/SQLite/Rust). Ships a CLI, MCP server, and agent skills; benchmarks 96.6% R@5 raw on LongMemEval with no API key.

RAG | Python · ai-memory · long-term-memory

CrewAI is an open-source Python framework for orchestrating role-based autonomous AI agents (Crews) and event-driven, controllable workflows (Flows). It ships a CLI for JSON/YAML project scaffolding, memory, tools, and optional enterprise control plane.

AI Agents | Python · multi-agent · agent-orchestration

Open-source 523-lesson, 20-phase AI engineering curriculum that builds math, transformers, LLM apps, agents, MCP and Agent Skills from scratch in Python, TypeScript, Rust and Julia. Ships installable Agent Skills (npx skills add) so a coding agent can tutor you lesson by lesson.

Skills | Python · curriculum · education

OpenManus is an open-source Python framework for general AI agents: tool use, Browser Use/BrowserGym browser automation, MCP servers, and multi-agent flows, with pluggable OpenAI, Anthropic, Azure, Google, or Ollama backends. Run one command to give an idea and let the agent execute it.

AI Agents | Python · multi-agent · computer-use

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.

AI Coding | Python · claude-code · codex

Flowise is a low-code/no-code visual builder for LLM apps: drag-and-drop nodes to compose AI agents, multi-agent workflows, chatbots and RAG pipelines on top of LangChain. Ships as a self-hostable Node/React monorepo with Docker and cloud options. Note: repo is archived.

AI Agents | TypeScript · low-code · no-code

Specify an app in natural language; the agent clarifies, then generates the codebase.

AI Coding | Python · Codegen · Agent

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.

AI Coding | Python · code-generation · cli

Meta's Segment Anything (SAM) is a vision foundation model that produces high-quality object masks from point/box prompts or fully automatic generation. The repo ships PyTorch inference code, checkpoint links, ONNX export, notebooks and a web demo.

AI Tools | Jupyter Notebook · image-segmentation · computer-vision

goose is an extensible open-source AI agent from the Linux Foundation, shipping as a native desktop app, CLI, and API. It works with 15+ LLM providers and 70+ MCP extensions to install, execute, edit, and test code or handle research, writing, and automation tasks.

AI Agents | Rust · ai-agent · desktop-app

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.

AI Coding | Python · agent skills · agile development

Fooocus is an offline, open-source SDXL image generator with a Gradio UI that removes most manual parameter tuning: you focus on prompt and image. It bundles a GPT-2 prompt engine, own inpaint/image-prompt algorithms, presets, LoRA and upscaling; runs on ~4GB VRAM. Now LTS/bug-fix only.

AI Tools | Python · stable-diffusion-xl · text-to-image

Curated awesome list of 5,400+ OpenClaw agent skills, categorized from the official ClawHub registry with spam, duplicates and malicious entries filtered out. Useful as a discovery index for finding and installing skills rather than as runnable code.

Skills | agent-skills · awesome-list

Official MCP server exposing Chrome DevTools to coding agents: it lets Claude, Cursor, Copilot or similar clients control and inspect a live Chrome instance for automation, network/console debugging, screenshots and performance traces. Also ships a standalone CLI.

MCP | TypeScript · mcp-server · chrome-devtools

Monorepo that renders deterministic MP4s from HTML, CSS, and seekable animations via CLI, SDK, or agent skills. Ships 20 Claude Code/Codex/Cursor skills so coding agents can plan, author, lint, preview, and render videos.

Skills | TypeScript · html-to-video · video-rendering

LlamaIndex is a Python framework for building LLM apps: data connectors, indices, retrievers and query engines for RAG, plus agent/workflow abstractions. 300+ integrations let you swap LLMs, embeddings and vector stores; the team now also pushes the hosted LlamaParse document platform.

AI Frameworks | Python · rag · llm

Markdown agent skill that rewrites AI-sounding text to read like a person wrote it, using 25 ranked patterns from Wikipedia's 'Signs of AI writing'. Installs via skills CLI or Claude Code plugin, works with any skill-capable agent, and preserves facts by asking rather than inventing.

Skills | Python · agent-skills · writing

A SKILL.md-style plugin that forces coding agents to lead with the action, number steps, cap lists and skip preamble, so answers stay ADHD-friendly and scannable. Ships hooks plus eval harnesses for Claude Code, Codex, Gemini CLI and OpenCode.

Skills | Python · claude-code-plugin · agent-skills

Multica is a self-hostable workspace where you assign issues to AI coding agents as teammates: agents pick up work on your own runtime daemon, comment progress, and hand back a diff for review. It drives 26 agent CLIs (Claude Code, Codex, Cursor, Kimi...) with execution logs, token cost tracking, squads, and autopilots

AI Agents | Go · agent-orchestration · multi-agent

Open-source book on AI agent design principles and engineering practice: full text in 15 languages, PDF/EPUB downloads, and 109 runnable companion experiments spanning context engineering, memory/RAG, MCP tools, coding agents, evaluation, post-training, and multi-agent collaboration.

AI Agents | Python · ai-agent · book

A collection of MIT-licensed Agent Skills (markdown workflow packs) that give Claude Code, Codex, Cursor, and other agents marketing expertise: CRO, copywriting, SEO/AEO, analytics, ads, and growth. Install as a plugin so your coding agent applies the right marketing frameworks on demand.

Skills | JavaScript · agent-skills · marketing

CLI-Anything converts everyday software into agent-native CLIs plus skills/plugins so AI coding agents can drive tools like Blender, FreeCAD, QGIS and game engines. Ships a CLI-Hub package manager, a skill generator, and marketplace plugins for Claude Code, Cursor and Codex.

AI Tools | Python · agent-native CLI · CLI harness

Cross-platform desktop app for upscaling and enhancing images with AI models such as Real-ESRGAN. Runs locally using NCNN and Vulkan, and requires a compatible GPU.

AI Tools | TypeScript · AI image upscaling · image enhancement

AIRI is an open-source, self-hosted AI companion and virtual character (waifu/VTuber) built on LLMs, with realtime voice chat, Live2D/VRM avatars, and agents that can play Minecraft and Factorio. Ships as web, macOS, Windows and mobile apps.

AI Agents | TypeScript · ai-companion · vtuber

Course repo (Made With ML) that walks through a full production ML workflow: data engineering, Ray-based distributed training/tuning, LLM fine-tuning in PyTorch, MLflow tracking, FastAPI serving and CI/CD. It is an educational reference implementation, not a reusable library or agent framework.

AI Tools | Jupyter Notebook · mlops · machine-learning

LocalAI is a self-hosted, OpenAI/Anthropic-compatible inference engine that runs LLMs, vision, voice, image and video models on CPU or GPU. Backends like llama.cpp, vLLM and whisper.cpp are pulled on demand, and it also ships agents, RAG and MCP support.

AI Frameworks | Go · llm-inference · local-inference

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.

AI Coding | Python · ai-pair-programming · cli

nanobot is a lightweight, self-hosted Python personal AI agent runtime. It runs in a WebUI, terminal, or chat apps (Telegram, Discord, Slack, WeChat, Email) with built-in tools, long-term memory, MCP support, multi-agent delegation, cron automations, and an OpenAI-compatible API.

AI Agents | Python · personal-ai-assistant · self-hosted

Indexes repositories into a code knowledge graph and exposes search, dependency, impact, and tracing tools through MCP for AI coding agents. Includes a CLI and web UI for repository analysis.

MCP | TypeScript · code intelligence · MCP server

CowAgent (formerly chatgpt-on-wechat) is a Python agent harness: it plans tasks, runs tools, installs skills, and keeps long-term memory plus a personal knowledge base. Multi-agent, multi-model, and multi-channel, deployable via one-line install or Docker.

AI Agents | Python · multi-agent · agent-harness

Local, agent-first skill control plane backed by 2,126+ SKILL.md playbooks. Agents search the catalog and pick skills; a read-only MCP plus CLI validate the stack and emit an immutable install plan before any change.

Skills | Python · agent-skills · skill-library

Library of 166 validated Agent Skills that give any standards-compatible AI agent scientific workflows: 100+ biology, chemistry and drug-discovery databases plus packaged skills for RDKit, Scanpy, Biopython, OpenMM and more. Installs as a skill pack or Agent Plugins package.

Skills | Python · agent-skills · ai-scientist

Milvus is a cloud-native distributed vector database for scalable ANN search over embeddings. It supports HNSW, IVF, DiskANN, GPU indexes, BM25 full text and hybrid dense/sparse search, making it a common retrieval backend for RAG and multimodal AI apps.

RAG | Go · vector-database · ANN-search

LibreChat is a self-hosted, multi-provider AI chat platform: one ChatGPT-style UI for OpenAI, Anthropic, Google, Azure, Bedrock and local models, plus agents, MCP tools, skills, RAG file chat, code interpreter, image generation and multi-user auth. Best for teams wanting a private, own-your-data ChatGPT alternative.

AI Tools | TypeScript · chatgpt-alternative · self-hosted

LibreChat is a self-hosted, MIT-licensed ChatGPT-style interface that unifies OpenAI, Anthropic, Google, Azure, Bedrock and local OpenAI-compatible endpoints in one UI. It adds no-code agents, MCP tools, skills, RAG file search, a sandboxed code interpreter, image generation, artifacts and multi-user auth for team depl

AI Tools | TypeScript · chat-ui · self-hosted

Kong Gateway is a Lua-based API gateway with LLM and MCP traffic capabilities. It routes requests across AI providers and adds controls such as semantic security, caching, observability, and MCP governance.

AI Tools | Lua · AI gateway · LLM gateway

Native C MCP server that indexes a codebase into a persistent knowledge graph using vendored tree-sitter grammars (162 languages) plus Hybrid LSP typing, answered via 15 MCP tools and Cypher at sub-ms latency. Single static binary, fully local, configures many coding agents automatically.

MCP | C · mcp-server · code-intelligence

Fabric is a Go CLI and REST API for applying reusable, task-specific AI prompt patterns to text, media, and other inputs. It supports multiple hosted providers and local models, and includes a web interface.

AI Tools | Go · AI prompts · prompt patterns

A Claude Code skill pack and slash-command workflow that turns an LLM agent into a job application assistant: scrape and rank postings, evaluate fit, generate tailored LaTeX CVs and cover letters, and prep interviews. Fork it, add your profile, own the data locally.

Skills | Python · claude-code · job-search

Rust-based CLI that gives AI agents headless Chrome control: open pages, snapshot the accessibility tree with element refs, click/fill/type, read agent-friendly text, screenshot, and invoke WebMCP page tools. Ships an MCP profile and skills, installable via npm, Homebrew, or Cargo.

AI Tools | Rust · browser-automation · cli

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

AI Coding | Go · code-review · cli

An Agent Skill (Claude Code, Codex, Pi, Factory Droid plugin) that generates editorial-quality diagrams as self-contained HTML+SVG, with ~50 layout types and importers for Mermaid, draw.io, and Excalidraw. No build step, JS, or external images.

Skills | HTML · agent-skills · diagrams

Agno is a Python framework plus AgentOS runtime for building, serving, and managing agent platforms. It adds REST/SSE endpoints, storage, memory, RAG knowledge, 100+ toolkits, human approval, scheduling, RBAC and OpenTelemetry observability, with Docker and cloud deploy templates.

AI Frameworks | Python · agents · multi-agent

LangGraph is a low-level Python orchestration framework for building stateful, long-running agents as graphs. It adds durable execution, checkpointing, human-in-the-loop interrupts, and memory, with optional LangSmith tracing and deployment.

AI Frameworks | Python · agents · multi-agent

AstrBot is a self-hosted Python agent chatbot platform that plugs LLMs, MCP tools, plugins, personas and a knowledge base into 15+ IM apps (QQ, Telegram, Discord, Slack, WeCom, Feishu, DingTalk). Ships Docker/CLI install, WebUI and a plugin marketplace.

AI Agents | Python · chatbot · multi-platform

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.

AI Coding | Rust · coding-agent · terminal

Curated awesome-list of Cursor Project Rules: Markdown .mdc files that give the Cursor AI editor project-specific guidance on frameworks, architecture, style, and workflow. Copy chosen rules into .cursor/rules/ to make generated code match your codebase. Rule quality varies by contributor, so review before adopting.

Skills | JavaScript · cursor · cursor-rules

A collection of agent skills encoding design and animation expertise for AI coding agents. Covers animation review/improvement, easing choices, Apple design, Swift, UI library selection, mobile-native fixes, and Sonner toasts. Install via npx skills@latest add emilkowalski/skills.

Skills | Markdown · agent-skills · design

OpenHuman is a Rust/Tauri desktop agent harness that builds a local-first memory tree from your accounts, then orchestrates fleets of sub-agents and durable workflows with MCP, skills and messaging channels.

AI Agents | Rust · agent-harness · agent-orchestration

A marketplace of coding-agent plugins, with 202 agents, 183 skills, 105 commands, and multi-agent workflows. It generates harness-native artifacts for Claude Code, Codex, Cursor, OpenCode, Antigravity, Copilot, and Pi from shared sources.

AI Agents | Python · coding agents · agent skills

Marker is a Python document-intelligence tool that converts PDFs, images, PPTX, DOCX, XLSX, HTML and EPUB into markdown, JSON, HTML or chunks. It runs local Surya VLM inference (vLLM/llama.cpp) for layout, OCR and tables, with optional LLM boosting for higher accuracy.

AI Tools | Python · pdf · ocr

LightRAG is a Python RAG framework that builds a dual-level knowledge graph over documents for entity- and relation-aware retrieval. It ships an API server, WebUI, multiple storage backends (Neo4j, Postgres, Mongo, Milvus, OpenSearch), reranking, multimodal parsing and OpenAI/Ollama/Gemini integrations.

RAG | Python · knowledge-graph · graphrag

A Claude Code plugin and CLI that adds teams-first multi-agent orchestration: /team and /autopilot spawn staged agent pipelines (plan, PRD, exec, verify, fix) plus MCP and tmux-backed CLI workers for parallel coding tasks.

AI Agents | TypeScript · claude-code · multi-agent

OpenMAIC is a self-hostable multi-agent platform that turns any topic or document into an interactive classroom: agent-generated slides, quizzes, simulations and PBL activities with AI teachers, whiteboard drawing, TTS and .pptx export. Ships a SKILL.md agent skill for OpenClaw, Codex and other workbenches, plus a chat

AI Agents | TypeScript · multi-agent · education

ByteDance's TARS stack ships Agent TARS (multimodal agent CLI/Web UI with GUI, vision and MCP tool use) plus UI-TARS Desktop, a native desktop app driving computer and browser operators from the UI-TARS vision-language model.

AI Agents | TypeScript · multimodal-agent · gui-agent

RVC WebUI is a PyTorch voice-conversion framework: train a custom timbre model from as little as 10 minutes of audio, then convert speech or singing vocals via CLI, Gradio WebUI, or a low-latency realtime voice changer. Includes RMVPE pitch extraction, HuBERT features, and pymss vocal separation.

AI Tools | Python · voice-conversion · voice-cloning

DSPy is a Python framework for programming rather than prompting LLMs: you write declarative modules and signatures, then compilers/optimizers (e.g. GEPA, MIPRO) tune prompts and weights against your metric. Useful for building and optimizing RAG pipelines, classifiers, and agent loops.

AI Frameworks | Python · dspy · prompt-optimization

Curated catalog of 500+ AI agent projects and use cases, with links to open-source implementations and self-contained runnable examples across CrewAI, LangGraph, AutoGen, Agno and LlamaIndex. Best for developers surveying agent frameworks and industry use cases rather than a usable library.

AI Agents | Python · multi-agent · awesome-list

VoxCPM2 is a tokenizer-free TTS system with a 2B diffusion-autoregressive model supporting 30 languages, voice design from text descriptions, controllable voice cloning, and 48kHz output. Ships Python API, CLI, Gradio demo, and vLLM-based serving.

AI Tools | Python · tts · text-to-speech

A large collection of hands-on Jupyter-notebook tutorials and runnable demos covering LLM apps, RAG pipelines, AI agents, MCP servers, fine-tuning and model evaluation. Best used as a learning/reference library of practical examples rather than a single installable product.

AI Agents | Jupyter Notebook · tutorials · llm

Anthropic's reference Claude agents, skills, and MCP data connectors for financial-services workflows: banking, research, PE, fund admin, and wealth management. Ships as Cowork/Claude Code plugins or deployable Managed Agent cookbooks, all file-based markdown and JSON.

AI Agents | Python · claude · agents

Colibrì is a pure-C, zero-dependency inference engine that runs frontier MoE models (GLM-5.x 744B, Kimi K3 2.8T, DeepSeek V4, Qwen3.x) on consumer hardware by streaming disk-resident experts into a unified VRAM/RAM/NVMe tier hierarchy. It offers chat/serve/web front ends plus CPU, CUDA, Metal and Vulkan backends.

AI Frameworks | C · inference-engine · moe

Khoj is a self-hostable personal AI app that answers questions from your docs and the web via semantic search and RAG, lets you build custom agents and scheduled automations, and works with local or online LLMs across web, Obsidian, Emacs, desktop and WhatsApp clients.

AI Agents | Python · ai-assistant · second-brain

Microsoft's official MCP server exposing Playwright browser automation to LLMs. It uses accessibility-tree snapshots instead of screenshots, so agents can navigate, click, type, and extract page data deterministically without vision models. Installable via npx into any MCP client.

MCP | TypeScript · mcp-server · playwright

CopilotKit is a TypeScript SDK for building agent-native apps: chat UI, generative UI, shared state, and human-in-the-loop across React, Angular, Vue, React Native, Slack, and Teams. It also maintains the AG-UI protocol connecting agent frameworks to frontends.

AI Frameworks | TypeScript · agent-native · generative-ui

PDFMathTranslate (pdf2zh) translates scientific PDFs into multiple languages while preserving formulas, tables, figures and layout, with optional OCR for scanned pages. It ships CLI, Gradio GUI, Docker, Zotero and MCP interfaces and supports Google/DeepL/OpenAI/Ollama backends.

AI Tools | Python · pdf-translation · document-translation

A security skill-router pack for AI coding clients (Claude Code, Cursor, Cline, Codex, Kiro) that routes agents to reverse-engineering, pentest, CTF, and malware playbooks instead of guessing commands. Includes routing configs, toolchain bootstrapping, MCP servers, and a regression-tested skill index across Windows, Ub

Skills | PowerShell · security · reverse-engineering

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.

AI Coding | Python · Claude Code · plugin directory

SGLang is a high-performance serving framework for LLMs and multimodal models, offering RadixAttention prefix caching, prefill-decode disaggregation, speculative decoding, and quantization over an OpenAI-compatible API across NVIDIA, AMD, TPU, and CPU hardware.

AI Frameworks | Python · llm-serving · inference-engine

Microsoft GraphRAG is a modular Python pipeline that uses LLMs to extract entities and relationships from unstructured text, build a knowledge graph, cluster communities, and answer queries with graph-based retrieval. Note: the repo is largely in maintenance mode with only bug fixes and CVE updates.

RAG | Python · graphrag · knowledge-graph

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.

AI Coding | TypeScript · coding-agent · ide-assistant

Python SDK for PageIndex, a vectorless RAG engine that builds a hierarchical tree index per document and lets an LLM reason over that tree to retrieve the right section. Supports local or cloud indexing, agent/MCP integration, and citations; no vector DB or chunking.

RAG | Python · vectorless-rag · reasoning-based-retrieval

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.

AI Coding | Go · coding-agent · terminal

Lightpanda is a from-scratch headless browser in Zig for AI agents and automation, ~16x less memory and ~9x faster than headless Chrome. It speaks CDP and WebDriver BiDi for Puppeteer/Playwright, and ships a native MCP server, an LLM-driven agent mode, and a skill.

AI Tools | Zig · headless-browser · browser-automation

QwenPaw is a self-hosted personal AI assistant built on AgentScope. It runs local or in the cloud, connects to chat channels (DingTalk, Lark, Discord, Telegram, iMessage), and extends via Skills, Plugins, MCP and a three-layer memory.

AI Agents | TypeScript · personal-ai-assistant · self-hosted

AirLLM is a Python inference engine that runs very large LLMs (70B up to 671B/2.8T) on a single 4GB GPU without quantization, distillation, or pruning by streaming model layers from disk. Optional 4/8-bit block-wise compression gives ~3x speedup, and it supports macOS/Apple Silicon plus low-VRAM training of 125B models

AI Frameworks | Jupyter Notebook · llm-inference · memory-optimization

Open source LLM engineering platform for tracing, evaluating, prompt management and debugging of LLM and agent applications. Self-hostable via Docker/Helm, with SDKs, OTel and integrations for LangChain, LlamaIndex, OpenAI and more.

AI Tools | TypeScript · llm-observability · llm-evaluation

Fully local, open-source ElevenLabs alternative for voice cloning, voice design, dubbing, dictation, transcription and audiobooks in 646 languages. Ships a desktop app (Electron/Tauri), model manager, local API and an MCP server for agent integration.

AI Frameworks | Python · voice-cloning · text-to-speech

Qdrant is a Rust-written, production-ready vector database and similarity search engine with REST/gRPC APIs, filtering, hybrid search, quantization, and sharding. It's a common retrieval backend for RAG, semantic search, recommendations, and image search.

RAG | Rust · vector-database · vector-search

Curated awesome-list of 1500+ Agent Skills from official vendor teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, Copilot and others. Useful as a lookup index rather than an installable tool; links out to individual skill repos/sites.

Skills | agent-skills · awesome-list

ChatDev 2.0 (DevAll) is a zero-code multi-agent orchestration platform: define agents, workflows and tasks in YAML, then run them via a FastAPI backend and Vue web console. Ships MCP support, memory, and Docker deployment for scenarios like research, data viz and content automation.

AI Agents | Python · multi-agent · orchestration

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.

AI Coding | Rust · self-hosted · code-completion

Buzz is a self-hostable Nostr relay workspace where humans and AI agents share the same rooms, channels, git events and workflows. Agents act as first-class members with their own keys, audit trail, JSON-only buzz-cli, and an ACP/MCP harness for Goose, Codex and Claude Code.

AI Agents | Rust · nostr · multi-agent

Python AI trading agent (LangGraph + LangChain) that turns natural-language requests into market research, backtests, and paper trades. Ships an MCP server, FastAPI backend, React UI, 18 broker/data connectors, and multi-agent swarm plus shadow-account trading.

AI Agents | Python · ai-agent · trading

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.

AI Coding | TypeScript · codex-cli · multi-agent

Prompt-as-Code library and gallery for GPT-Image-2/2.5: 530+ cases, 20+ industrial templates, and an installable agent Skill. Includes a Vite/React site with prompt search, generation testing via async image APIs, and a 2.5 shared-prompt comparison view.

AI Tools | JavaScript · image-generation · prompt-library

GitHub's official MCP server that connects AI agents and assistants to GitHub's platform, exposing tools for repositories, issues, PRs, Actions, code scanning and discussions. Runs remotely via GitHub Copilot's hosted endpoint or locally via Docker with OAuth or PAT auth.

MCP | Go · mcp-server · github

Apache-2.0 library of 818 structured cybersecurity skills for AI agents, following the agentskills.io standard with YAML frontmatter and Markdown workflows. Skills map to MITRE ATT&CK, NIST CSF 2.0, ATLAS, D3FEND, NIST AI RMF and MITRE F3, and load into Claude Code, Copilot, Codex CLI, Cursor, Gemini CLI and other plat

Skills | Python · cybersecurity · agent-skills

Fish Speech (Fish Audio S2 Pro) is an open-source 4B multilingual TTS system using a Dual-AR transformer plus RVQ codec, GRPO alignment and inline [tag] prosody control. It supports voice cloning, streaming inference via SGLang, and ships a Gradio WebUI and API server.

AI Tools | Python · tts · text-to-speech

AgentScope 2.0 is Alibaba Tongyi's Python framework for building and running production agents: ReAct agents, toolkits over Python/MCP/skills, multi-agent teams, realtime voice, sandboxed execution, HITL, memory, plus a FastAPI agent service with web UI and IM channels.

AI Frameworks | Python · multi-agent · agent-framework

CLI tool that fully automatically strips refusal behavior ("safety alignment") from transformer LLMs using directional ablation plus Optuna-based parameter search, minimizing refusals while preserving the original model's capabilities.

AI Tools | Python · abliteration · llm

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.

AI Coding | TypeScript · coding-agent · terminal

Onyx is a self-hosted AI knowledge platform that indexes content from 50+ apps for permission-aware enterprise search and agentic RAG. It also provides AI agents, deep research, web search, MCP access, and integrations with hosted or local LLMs.

RAG | Python · agentic RAG · enterprise search

A C++20/Qt6 native desktop financial research terminal with embedded Python analytics, 100+ market data connectors and QuantLib tooling; AI agents and BYO-LLM-key features are optional extras. Primarily a finance/quant product, not an AI developer tool.

AI Tools | C++ · finance · trading

Local-first code knowledge graph that parses repos with Tree-sitter into a persistent SQLite graph and serves MCP/CLI queries so AI coding tools read only affected files. Includes blast-radius analysis, incremental updates, risk-scored PR CI action, and a VS Code extension.

MCP | Python · code-review · knowledge-graph

STORM researches topics through web retrieval and multi-perspective LLM conversations, then generates outlined reports with citations. Co-STORM adds collaborative human-AI discussion and a dynamic mind map.

RAG | Python · deep research · agentic RAG

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.

AI Coding | Python · claude-code · cli

OfficeCLI is a free, open-source single-binary CLI that lets AI agents read, create, and edit Word, Excel, and PowerPoint files without installing Office. It ships an agent skill file and an HTML/PNG rendering engine so agents can view and iterate on documents.

AI Tools | C# · office-automation · docx

Privacy-first desktop AI meeting assistant built with Tauri and Rust. Runs Whisper/Parakeet transcription, speaker diarization, and LLM summaries fully locally via Ollama, with optional Claude, Groq, or OpenAI-compatible endpoints. macOS/Windows/Linux.

AI Tools | Rust · meeting-assistant · transcription

Python framework for building temporal knowledge graphs that give AI agents time-aware memory. Ingests structured and unstructured episodes into Neo4j/FalkorDB and serves hybrid semantic+keyword+graph retrieval. Ships an MCP server.

RAG | Python · knowledge-graph · temporal-graph