Code agents

Persistent structured memory for Claude Code. No infrastructure required — just markdown files and git.

AI-powered codebase analysis platform using static analysis, graph traversal, vector retrieval, and LLM review agents.

AI-powered system for mapping clinical text to Human Phenotype Ontology (HPO) terms using Retrieval-Augmented Generation (RAG). Features Python CLI/library, FastAPI backend, and Vue.js frontend for interactive phenotype extraction from medical texts.

A modular, multi-model AI assistant UI built on .NET 9, featuring RAG, extensible tools, and deep code + database knowledge through semantic search.

A Simple and Opinionated AI RAG Solutions for SourceCode

A web application that helps you preserve and visualize your personal relationships and shared memories. Store photos, audio notes, and text about the people in your life, and see how they all connect through an interactive relationship graph.

对任意it项目生成生成 ai上下文到一个单独文档，传给ai大模型或者知识库，把生成的文档传给 google ai studuio ，对大型编程项目的代码生成准确率，效果远远地吊打在 cursor trae qoder claude-code gemini-code-assit 等ai ide写代码

Hybrid AI system that uses OCR, ML, and RAG-powered LLMs to turn legal documents into plain-English explanations with risk flags.

The open-source benchmark for LLM memory decay. Measure how Naive, RAG, Chunked RAG, Cascading, and SummaryMemory degrade over 100 conversation turns. Ebbinghaus forgetting curves, 5-provider LLM eval, multi-seed CI. No API key needed.

🧬 RAGIX: Local-first development assistant making LLMs behave like disciplined engineers – Unix-RAG retrieval, sandboxed execution, MCP-compatible, fully auditable

AI-powered multi-agent system for automated proposal generation using context-aware retrieval and persona-based writing.

🚀 Production-ready modular RAG monorepo: Local LLM inference (vLLM) • Hybrid retrieval with Qdrant • Semantic caching • Docling document parsing • Cross-encoder reranking • DeepEval evaluation • Full observability with Langfuse • Open WebUI chat interface • OpenAI-compatible API • Fully Dockerized

macOS app to chat with your local documents

Explore Mistral AI's extensive collection of models. Learn to select, prompt, and integrate Mistral's open-source and commercial models for tasks like classification, coding, and Retrieval Augmented Generation (RAG).

This guide covers project structure, environment setup, running Qdrant (Docker), starting the Web App, setting OpenAI secrets, ingesting sample data, and testing with the provided question list.

TreeRAG: Hierarchical RAG platform that indexes dense PDFs into logical trees for precise retrieval, 100% traceability, and LLM-guided deep traversal. Production-ready with enhanced security and streaming indexing.

pure c# wpf implement for llm chat client.

The "SQLite for Vectors" in pure Go. Embeddable, HNSW indexing, CGO-free, and Qdrant-compatible API.

Self-Evolving RAG System with ChromaDB for continuous knowledge updates (6x daily), designed to overcome Large Language Model data cutoff limitations.

Dive into the brand new OpenAI Assistant API, focusing on tools like retrieval and functions.

Capture every prompt. Own the signal. A Claude Code plugin that logs every prompt to .prompts/ in your repo, automatically.

🚀 Generate and extend production-ready Model Context Protocol (MCP) servers with a modern CLI tool that showcases all MCP features in one cohesive example.

A virtual filesystem alternative to MCP — expose tools to LLMs via file I/O

nv:context > Context engineering for engineers who ship. Auto-detects, analyzes, generates configs, hooks, session management, and token budgets. 200+ research sources.

The grainulation ecosystem. Structured research, decision-making, and knowledge management for AI agents.

CLI tool to format codebases for DeepSeek R1 and Claude 3.5

PII redaction that preserves data format, tokenized values stay usable in LLM pipelines

Autonomous deep-research platform powered by Hermes Agent. Multi-phase pipeline with parallel research, self-critique, iterative refinement, and real-time streaming.

AI-Resume is a containerized web application that acts as your digital professional proxy. Transform your CV into a conversational agent.

AI-powered GitHub repository analyzer that ingests full codebases, enables codebase-wide chat, detects bugs, and suggests optimizations using RAG (LangChain + FAISS + OpenRouter) with a Streamlit UI.

Autonomous AI agent system with local-first control, plugins and web/CLI interface.

The Universal App Store for AI Agents. Discover & Install Skills for Claude Code, Cursor, Windsurf, Aider, Codex & Gemini.

MCP server with specialized judges to evaluate AI-generated code for security, cost, scalability, cloud readiness, and best practices.

Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud.

BACH v3.13.0-bluesky: local-first text-based OS for LLM agents with SQLite memory, 113+ handlers, 550+ tools, MCP servers, scheduler and multi-agent orchestration

AI Agent Skills for SEO auditing , 11 SKILL.md files that teach Cursor, Claude Code, Copilot & more to perform comprehensive SEO audits. Zero dependencies.

Run a full AI agent on mobile with local LLM calls, on-device memory, code execution, and native HTTP support in Capacitor apps.

An unofficial fork of OpenAI Codex with multi-account ChatGPT and one-command local models via LM Studio. Save every plan, hop between them mid-task, fall back to a model on your own machine when you want to.

Lightweight self-hosted AI agent platform. Simple / Pipeline / Handler execution modes, hybrid RAG, knowledge graph.

AI-powered skill discovery tool for finding and recommending agent skills across 8+ platforms

Persistent memory for Claude Code — invisible self-annotating metadata, semantic search, cross-project retrieval

Security research methodology for AI agents — attack patterns, decision trees, techniques, and payloads organized by vulnerability type

Production-ready AI AppSec skills for SAST, threat modeling, remediation, PR security review, and serialization abuse analysis.

Persistent memory for Claude Code & Codex CLI. Capture knowledge from sessions, compile it into a wiki, and inject the right context back into future work.

"From Prompt to Cognitive Engineering". — AI: Designed, not Dreamed.

Workflow management CLI for Anthropic Claude Code, Cursor, and Gemini CLI. 30 AI agents — incl. a virtual eng team — 84 commands, 62 skill categories. Built for Claude Opus & Sonnet.

Bayesian memory that learns from feedback for LLM agents

A coding agent built based on the LangChain / LangGraph ecosystem

🚀 Monitor your Claude Code sessions effortlessly on macOS with real-time status updates and quick access features for a streamlined development experience.

Modern enterprise-grade shipping carrier API clients & MCP servers for AI assistants

A self-improving system of 7 AI skills that chain together to solve hard problems. Built for Claude Code.

Governance harness for Claude Code & Codex CLI — 57 MCP tools, 45 quality-gate hooks, 64 enterprise skills, HMAC-signed evidence, 2FA infrastructure locks. Vibe prompt in, enterprise quality out.

Multi-agent collaborative development skill for OpenClaw — Gemini(design) + Claude Code(logic) + Codex(review) | 多Agent协作开发，7轮双盲测试验证

The harness your agents grow in.

切腹 — a skill that makes your coding agent atone for unforgivable mistakes: a formal apology, ASCII seppuku, and a ~/.seppuku ledger it learns from. Concept by @allgarbled.

Local, privacy-first agentic coding workspace in Go. CodeDone breaks large dev tasks into atomic serialized tickets, dispatches AI implementers one step at a time, and uses a Contre-Maître system to plan, supervise, review, and finalize work with lower token waste and higher reliability. Built to excel at very long tasks spanning multiple days.

Twelve animals. Twelve LLM defaults. Pick the ones your AI won't break on its own.

Local-first Personal OS + Markdown Wiki for AI agents: LLM Wiki-style knowledge graph, task claiming, and reviewable execution

Local-first persistent memory for AI agents — store, recall, and consolidate knowledge across sessions using FAISS, SQLite, and any LLM. MCP server for coding agents and any MCP client.

Per-task spend ceiling for AI agents. One task_ref, and preflight answers approved: false once that job is out of units. An SDK and an HTTP API, not a proxy.

Specialized AI agents for DeFi, crypto, blockchain, Web3, DeFAI. Deep expertise in yield optimization, smart contracts, portfolio management. Multi-agent collaboration (Agent Teams), MCP (Model Context Protocol) integrations, universal JSON API. Open-source, no vendor lock-in, 18 languages.

Local-first memory and prompt-cache layer for Claude Code

a collection of examples and reference implementations for working with the Timbr LangChain SDK, LangGraph, and GraphRAG. The examples demonstrate how to use Timbr's ontology-driven semantic layer, natural language interfaces, and graph-based orchestration to build advanced data and knowledge applications

OmniClaw by Long Leo (Ha Dinh Long) — a Claude Code & Antigravity agent OS governed by 8 immortal Python daemons: zero-trust Git guard, 3-tier MemPalace memory, no agent free-will. Not affiliated with other projects sharing this name.

Persistent memory engine for AI agents. MCP-native. SQLite + FTS5 with PQC security. Multi-agent orchestration with zero-trust architecture.

🐟 Suanfish Design System — 33 specialized AI design agents across 7 tiers with REJECT mechanism. Multi-agent design language SKILL for Claude Code / Codex CLI / Copilot CLI. v2.5 adds AI-native Path G (streaming · tool-calls · reasoning · citations · artifacts).

Local web GUI for Claude Code and Codex with builder/breaker loops, manual cross-agent review, and Git diff timelines.

agent-skill for p2claw - peer to peer app delivery

A repository of Claude Code Plugins - Swift, SQL, PowerShell, Rust Agents w/Skills and Hooks

AutoMCP scaffolds your Model Context Protocol config from package.json deps

NLIP’s Security Guidelines and Best Practices is the companion to the NLIP core specification, brought to you by the NLIP Security Working Group.

Make development work feel lighter.

An Intelligent Biomedical Semantic-Retrieval System

Standardizing identity and connection orchestration for autonomous agents. A provider-agnostic, zero-trust framework for managing API integrations, OAuth2, and OIDC for in multi-agentic networks

Local-first GenAI lab with a React frontend and Spring Boot backend, supporting Ollama, Amazon Bedrock, Hugging Face, RAG document retrieval, MCP-backed AWS tools, streaming chat, persistent sessions, and artifact/report workflows.

Turn your Windows GPU into a private, low-latency LLM server. Docker-based, OpenAI-compatible API.

Personal Knowledge Management (PKM) with voice journaling, Claude Code skills, and AI-powered knowledge distillation. Markdown + Git.

Lightweight Go SDK for Yandex Messenger Bot API — type-safe client with retry, rate-limit handling, and service-oriented architecture

🆓 Access a collection of free, public JSON APIs with no limits or authentication required. Explore e-commerce, jokes, movies, and more.

AI-powered fitness coach with multi-provider support (Claude, GPT, Ollama). PWA with 27 MCP tools, workout planning, and progress tracking.

About Chat with any website using FastAPI, Next.js, and the latest LangChain version for seamless integration.

Ask any question to your documents, PDFs, or SQL databases using GenAI for quick and accurate answers.

Private, secure, AI chatbot interface to serve locally or host on an HTML. This simplified interface and minimal file format aims to provide a framework easily built and expanded on as the field of AI continues to grow. Highly customizable with a visual editor. Currently in the early stages: Development is happening rapidly.

My personal agent skills — JVM profiling, GC, concurrency, distributed systems. Compatible with Claude Code, Codex, Cursor, Cline, and any agent that supports the skills.sh format.

Application for comparing responses from different Large Language Models (LLMs) side-by-side

OpenAI-compatible local proxy for Kiro CLI (Amazon CodeWhisperer) — Claude Opus 4.7, Sonnet 4.6, Haiku, DeepSeek, Qwen, GLM as OpenAI API

A mildly sane inference API library for go

A RAG-based chatbot that extracts insights, summaries, and topic clusters from YouTube videos, providing comprehensive understanding and answering user queries.

Zero-config LLM call inspector. See every API call your AI app makes.

The ultimate MiniMax 2.7 Highspeed Claude Code harness - 100 TPS, 204K context, GStack skills, 5-tier memory, 10x productivity.

Let your AI agent use X (Twitter) on your behalf — post, reply, search, DMs, bookmarks, and more.

Cut Claude Code token usage 50–80%. Auto-generates a codebase index so Claude finds files instantly instead of reading everything.

Figma plugin that scrapes any live URL and rebuilds it as native Figma frames — auto-layout, fills, strokes, typography. Built for piping Claude-generated UIs back into Figma.

Rubric-driven AI homework grading system built as a Claude Code Skill. Score student submissions with CoT reasoning, bias mitigation, and PDCA quality cycle.

The living wiki that writes itself.

💻 Build and manage projects efficiently with the OpenCode Web UI CLI, featuring a chat interface, file previews, and model selection.

Test lab for RAGdrag — vulnerable RAG target, sample results, and test suite

bondage-core is the local C launcher/policy engine.

Local Sandbox Runtime for AI Agents. Run AI-generated code safely with OS, Wasm, and microVM isolation.

AI-powered fundraising ops built on Claude Code. Skill modes for investor scanning, pitch-deck refresh, accelerator applications, and follow-up cadence. Batch processing, PDF generation.