Code agents

Open-source cross-platform compatibility layer for using Codex GPT models in Claude Code

A transparent same-protocol LLM proxy that routes cheap tasks to Flash and hard ones to Pro by structural signals — no keyword guessing.

SQL Server 2025 demo: graph (SHORTEST_PATH) + vector (DiskANN) + Blazor Server. SQL Server 2025: Herkes İçin, Her Rol İçin kitabının referans uygulaması.

Video Memory CLI: index once, search/ask forever (dense captions + transcripts + timestamps). Built for agents.

Financial Q&A for Indian equities. Deterministic ratio engine + RAG-powered LLM for NSE/BSE companies. CLI, API, dashboard.

Open-source platform for building AI agents with long-term memory, multi-channel support (Telegram, Slack, WhatsApp) and an OpenAI-compatible API

Evidence-first product teardown skill for any AI product: journeys, agents, models, tools, context, knowledge, evaluation, safety, and architecture.

Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware table pruning for LangChain, MCP and any SQL agent. Postgres, Oracle, MySQL, SQL Server. 75% fewer prompt tokens.

AI-powered LeetCode analytics platform — syncs your solving history and uses RAG (Gemini + ChromaDB) to answer personalized questions about your strengths, weaknesses, and growth areas. Built as a Turborepo monorepo with real-time SSE sync, BullMQ background jobs, and full observability (Prometheus/Loki/Grafana)

A framework for Forward Deployed Engineers: from problem statement to a deployable AI project — every decision traced to a fact, every fact to a source.

Build provenance-aware higher-order knowledge graphs and native hypergraphs from documents, with validation, semantic search, and offline visualization.

短视频解析 · AI 剧本复刻 · 一键成片 | LangGraph 多 Agent 流水线

Sentence-level RAG factual grounding and hallucination detection engine

Desktop app for Claude Code: a roster of bots, each with its own model, working directory and persistent conversation

AI agents and skills for mobile development: Flutter, Android, iOS and React Native. Plugin for Claude Code and Codex.

中国软著登记材料生成器：源码进去，页数一页不差的 PDF 出来

VinusCLI - the AI coding agent in your terminal. Docs, issues and releases. Ships via npm; source is closed.

Multi-tenant security isolation guard enforcing memory boundary compartmentalization

Open-source YouTube Music client for Android and Windows build with arena.ai

一个用 TypeScript 构建的多智能体学习与实验场：基于 DeepSeek Responses API，从零实现强类型 Agent Loop、工具调用回填、Skills 按需加载和 SQLite 会话持久化，并以 Gexep、Lexey、Jezeh 等角色“粘合”邮件、E2B Sandbox 等能力，以及对 MCP、A2A、最小权限协作和 GraphRAG 长期记忆的探索与思考。

Speculative decoding draft-model verification engine calculating acceptance probabilities

Customer review aspect-level sentiment mining engine extracting satisfaction radar breakdown

Acoustic vocal emotion, prosodic valence, and customer frustration analyzer

The governed context layer for production AI agents.

Self-hosted AI agent harness: web UI + HTTP API, sandboxed tool execution, persistent workspace memory, selection quoting, browser and computer use. TypeScript, zero runtime deps, one command to start.

Autonomous refund and dispute arbitration engine validating carrier proofs and policies

Integrate the powerful PI coding agent directly into VS Code with a user-friendly GUI.

Per-turn model routing for the Pi coding agent: a small judge picks the cheap or the strong tier for each message, with multi-model failover, task-level orchestration, and an optional decision-model judge (Jev) that answers with a calibrated probability instead of prose.

Self-hosted reverse-engineering workspace API — orchestrates jadx/apktool/adb/frida/APKiD via a job & workflow engine, exposed as native MCP tools for Claude. No cloud required.

Code for "When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis" (arXiv:2609.15309) — paper: https://arxiv.org/abs/2609.15309

An open-source framework for building stateful, multi-agent AI applications. It helps developers create reliable AI workflows with memory, human-in-the-loop capabilities, tool calling, and long-running agent orchestration.

Discover campus events, find teammates and stay connected. A bilingual full-stack app with Spring Boot, MySQL, LangGraph support and Docker Compose.

Local-first Windows desktop workspace for Codex, OpenCode, Cursor Agent, GitHub Copilot, Gemini CLI, and other AI coding agents.

Captain Code: one terminal for every coding agent you already pay for. Local director routing across Claude Code, Codex, Cursor, and remote models via opencode.

An LLM-harness fleet boost framework for Claude Code, Codex & OpenCode — turns your AI coding agents into a disciplined engineering team you can see, message, and hold to the rules.

A programmable AI agent harness built in Rust and configured with Lua. Create custom coding agents with a terminal UI, multi-provider LLM support, MCP tools, persistent sessions, and an extensible plugin system.

Self-hostable multi-agent AI workbench — LangGraph-orchestrated expert teams, human-in-the-loop plan approval, live run timeline. FastAPI + React + PostgreSQL.

RavenClaude — private Claude Code plugin marketplace: governed multi-agent teams, Thing tribunal, comfort-posture dashboard, Runes ready-queue, Prompt Builder, plugin lifecycle, and 184 plugins. Level up from one Claude to a full AI engineering org.

Dual-harness Kimi K3 collaboration for Codex: native subagents plus observable Kimi Code sessions.

Autonomous hierarchical multi-agent team (CEO -> Manager -> Workers) for Model Context Protocol (MCP). Mix Claude Code, Antigravity, Codex & Direct API with persistent SQLite queues and a real-time web UI.

Multi-agent orchestration setup for OpenAI Codex: a root orchestrator with scout, builder, verifier, scholar and critic subagents. Pro, Plus and Lite plans.

A terminal CLI that runs multiple AI coding agents from different LLM providers concurrently on one project. Install now!

A minimal Codex skill that delegates work to specialized agents and verifies the result.

Enforceable, provider-neutral harness for multi-agent AI coding: spec-driven workflow, cross-provider peer review, and safety rails. First-class for Claude Code and Pi; advisory adapters for Cursor, Codex, Copilot, Windsurf, and Aider.

Your AI coding agents live on your computer. Relay puts them in your pocket.

Signal double ratchet state machine advancing symmetric KDF chains and ephemeral Diffie-Hellman keys for forward secrecy.

FRI (Fast Reed-Solomon Interactive Oracle Proof of Proximity) folding engine verifying polynomial low-degree bounds for STARKs.

Production-grade genpark-geohash-spatial-quadtree-encoder-skill skill for AI agents

Production-grade genpark-hamming-7-4-syndrome-decoder-skill skill for AI agents

Zero-trust governance middleware for Model Context Protocol deployments

Multi-account switcher for Claude Code and Claude Desktop: claude-swap (cswap) plus a maintained patch series.

Open-source LLM application development platform that combines AI workflows, RAG pipelines, agents, model management, and observability to help teams build and deploy production-ready AI applications.

Intelligent token and context optimization for Claude Code — an Agent Skill + CLI that makes Claude smarter about what it consumes.

Cut Claude Code's skill manifest by ~75% with TypeSafe Jev. Scores every installed skill for relevance and hides the rest via skillOverrides — 12,750 → 3,185 tokens on a 217-skill install, for $0.0009 a session.

macOS menu bar AI usage monitor for multiple Claude and Codex accounts: quota, rate limits, and a smart launcher for Claude Code.

Open-source cross-platform compatibility layer for using Codex GPT models in Claude Code

Protocol-faithful, multi-provider AI gateway for OpenAI, Anthropic, Gemini, and OpenAI-compatible APIs — native wire types, streaming SSE, zero lowest-common-denominator abstractions.

55 production-grade Google Cloud data engineering projects in Python — BigQuery, Dataflow/Apache Beam, Composer/Airflow, Pub/Sub, Dataproc, Vertex AI, Gemini, RAG, MCP. Live-tested on GCP.

Lightweight QMD alternative: fully local hybrid search engine (BM25 + vector + rerank) and MCP server in a single ~15MB Go binary. No Node.js. Runs on Raspberry Pi.

Self-hosted orchestration layer for autonomous AI agent teams. Shared memory, heartbeat scheduling, vault-first secrets, and cross-model peer review — one command to deploy.

Local-first semantic memory engine for AI agents - scores, trusts, and forgets so your agent stops making the same mistake twice.

FriendlyClaw 🦀 — Pro-Grade Autonomous Hive Operative. Multi-agent delegation, semantic RAG memory, and proactive system control.

Secure credential management for AI agents

The dashcam and emergency brake for AI agents. A security proxy that physically blocks rogue LLM commands and generates cryptographically proven audit trails for enterprise compliance.

🌟 Mindstride is a RAG-based chat assistant designed to support mental health, personal growth, and self-improvement. This project leverages advanced AI technologies to provide a personalized and insightful experience, drawing from the wisdom of over 70 books on mental well-being, personal development, and self-discovery.

🤖 一个基于本地 Ollama 模型的代码助手 CLI 工具。集成 LangChain.js，使用模型原生 tool calling 能力实现可靠的工具调用。

📝 Streamlit App : Weekly News Letter Crew AI Agents 🖋️

A centralized API management platform with user authentication, service versioning, collaborative API development and most valuable, automatic frontend code generation. Built with Python/Robyn backend and React/TypeScript frontend.

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from

a startup but not simple agent demo using google adk.

An LLM-first AEO analysis skillset for Antigravity, Codex, Claude, Gemini, OpenCode, etc. with 6 specialized sub-skills, 6 specialist agents, and 5 optional utility scripts used as evidence collectors

These #LangChain-powered apps include a Research Assistant that generates reports using web scraping and GPT-4o-mini, and Chat With Video, a #Streamlit app that #transcribes videos and enables content-based Q&A via #embeddings.

Transform your terminal into an intelligent AI workspace with autonomous tool-calling and multi-step workflow execution, real-time streaming responses, persistent chat history, and comprehensive MCP (Model Context Protocol) client functionality for seamless tool integration.

Go client library for interacting with the Anthropic safety-first language model REST APIs.

FastAPI Local RAG Q&A Demo

Production-ready Agent Runtime for Claude Code — Dashboard visualization, Team mode, Plugin daemons, Memory system, and one-command setup

AI Agent 小红书短图文 Skill — 选题优先级 + 四维评分 + 钩子库 + 反 AI 味

The first MCP server for Guesty property management. 38 tools for reservations, guests, messaging, pricing, financials, calendars, reviews, tasks, webhooks, and more. Connect AI agents to your Guesty account.

Self-evolving AI assistant starter kit. Markdown-only. Works with Claude Code, Codex, Devin, Cursor, and any LLM agent

✨ AI Agent that uses tools and functions to autonomously complete multiple tasks.

The most flexible control plane for AI Agent systems

Agent Skill: TYPO3 extension conformance checker - validates against official standards | Claude Code compatible

Skills, extensions, and packages for the Pi coding agent

HIEF (Hybrid Intent-Evaluation Framework) Persistent Memory Layer for AI Coding Agents

Koro — voice-first AI agent that actually does things. Search, code, execute — all via Telegram voice.

Production-grade evaluation framework for Text-to-SQL and SQL AI agents. 50 metrics. Any LLM. pip install sqlas.

A conversational AI CLI that brings MiniMax's intelligence directly to your terminal. Edit files, run commands, and manage projects through natural language with lightning-fast code editing

Claude Code -powered Research, Orchestrated.

AI agent skills for Jamdesk documentation workflows — Claude Code skills, automations, and coding agents

X/Twitter research agent for OpenClaw and Claude Code. Search, filter, monitor — all from the terminal. Powered by TwitterAPI.io.

An intelligent AI-powered system designed to simulate, monitor, and analyze malicious interactions

A GitHub bot that supercharges spec-driven development through automated generation of Cloudflare Workers.

Your personal Claude Code agent, running 24/7 in the cloud. Talk to Claude from Telegram, Discord, or the web — with memory, tools, and automation.

ACP bridge provider for pi — use Claude Code, Codex, and Gemini via official ACP with session persistence and MCP/entwurf orchestration.

AI Code Mentor is a runtime environment designed for building applications with integrated autonomous AI agents.

A secure database access gateway for AI Agents: Empowering LLM (Agents) with database access capabilities.

MCP server giving Claude live access to SAP systems via ADT — read, edit, search, test, and diff ABAP across landscapes without installing anything on the SAP stack.

Your agent docs lie. Nerviq finds the lies in 30 seconds — stale references, permission exposure, and cross-platform drift in CLAUDE.md / AGENTS.md / Cursor rules. Deterministic, zero dependencies, MIT.

A5:DB Document. Create DB Schema layout document for AI Agent.

ACTS: Agent Context Tree Standard - A feature-first context protocol for AI Agents.