Code agents

🤖 Multi-agent AI code reviewer & documentation generator powered by CrewAI, Google Gemini 2.5 Flash, and Streamlit.

Runnable Jupyter notebooks for Maida: trace an agent, capture a baseline, and gate a behavioral regression -- with LangChain, LangGraph, OpenAI Agents, and CrewAI. No API keys, no network calls.

Code samples connecting Python agentic frameworks (LangChain, LlamaIndex, CrewAI, ...) to LucidLink via the Python SDK and MCP server

AI LegalAdvisor, AI ContractsAnalyst, AI LegalStrategist, and AI Team Lead With Agno

Deterministic approval, rejection, cancellation, timeout, replay, and side-effect safety tests for AI agents—no API keys required.

Long-running autonomous hierarchical multi-agent software development engine for terminal, web, and Android. Local-first, multi-provider, open source. Not another a chatty prompt-driven session.

The delivery loop for autonomous software factories

A safety layer for AI agents; it decides what your agent is allowed to do - and proves it.

🗣️ AgentRound — 多模型 AI 圆桌讨论框架。让多个 AI 模型围绕同一主题展开多轮辩论，支持并发调用、人类实时介入、智能 Token 裁剪、Rich 终端渲染和 Markdown 导出。兼容任意 OpenAI 兼容 API。

Codex-native Claude review plugin for read-only, evidence-cited Opus review lanes.

Built for AI agents: drive and debug a running app from one config file, and come back with proof a person can watch and an agent can read — not a pass/fail, and not a guess.

Governed, auditable AI review platform: the review and approval work a team does by hand, as a webhook-triggered LangGraph agent with human-in-the-loop approval, Langfuse tracing, an eval-gated CI pipeline, and a tamper-evident hash-chained audit trail. Provider-agnostic (mock/Anthropic/OpenAI), FastAPI, Bicep IaC for Azure Container Apps.

RSI-EAF: XRPL-grounded autonomous factory. LIVE x402 merchant — pay testnet Tag 1/2. https://published-zeta.vercel.app/pay.html

MCP server that brings Perplexity to Claude Code — AI-powered web search, deep research, reasoning, and real-time citations. 9 tools: search, deep research, reasoning, raw search, Q&A, code review, brainstorming, explanations, and file analysis.

Islamic-knowledge AI service for DeenBridge — FastAPI + Gemini assistant with verified Qur'an/Hadith citations, scholar-review fallback, and guidance for Stellar/USDC payments.

智密浏览器 Zhimi Browser — 基于 Chromium 源码级定制的国密（TLCP/SM2/SM3/SM4）+ 大模型 AI 浏览器。A GM-crypto (TLCP/SM2/SM3/SM4) + LLM browser built on Chromium.

Production-ready MCP servers for GitHub, Bitbucket, GitLab & Jira - enabling AI assistants to interact with your dev platforms

AI-powered e-commerce trust platform with multi-LLM review analysis, fake review detection, and smart product recommendations

SelfGPT: secure multi‑provider LLM chat with PDF RAG, web search, and LangSmith tracing.

Live chat + webrtc video call with AI takeover for multiple websites

Чат с искусственным интеллектом для Android с авторизацией через Telegram/VK, историей чатов, инструментами для работы с изображениями и файлами, экранным помощником, общими чатами и бэкендом на Node.js/PostgreSQL.

支持 VRM/VRMA、语音状态联动与 MCP 控制的跨平台桌面虚拟角色｜中文界面与可配置动作库

个人财务操作系统：账户/流水/负债/应收款管理，Financial Engine 实时计算资产负债，LLM 配置中心 + DeepSeek AI 只读财务分析助手。Vue3 + FastAPI + PostgreSQL + Docker

gguf text-generation base_model:Kwaipilot/KAT-Coder-V2.5-Dev base_model:quantized:Kwaipilot/KAT-Coder-V2.5-Dev endpoints_compatible region:us

gguf quantized GGUF imatrix quantization imat

Deterministic two-layer validator for LLM tool calls: stdlib structural checker in 25,000-case differential agreement with pinned jsonschema, plus the semantic contract layer where real failures live - qwen2.5-7B: 0 schema violations, 7 semantic, replayed in CI from committed data.

Open-source multi-agent governance for running multiple AI coding agents in parallel on one GitHub repo: issue claiming, task market, strict CI/CD gates (GATE-1..6), auto-merge. Install via npx, curl bootstrap, or Codex/Claude marketplaces. Any agent (Codex, Claude Code, Cursor) — no daemon, no vendor lock-in.

适配 DeepSeek Harness 的 OMO 规约智能体与超任务编排工具，用于不间断任务规划、分类委派与自主校验。OMO‑style discipline‑agent + ultrawork orchestration toolkit for DeepSeek Harness, for endless task planning, categorized delegation and self‑verification.

Ask your data. Trust the answer. — A text-to-SQL product for non-technical users.

WordPress performance audit and optimization skills for AI coding agents — Core Web Vitals, caching layers, page builders, and managed-host constraints.

PikoClaw 2026: Rust-Powered AI Agent for High-Performance Devleopment

macOS APFS transparent compression for cold agentic-CLI session JSONLs (Claude Code, Codex, Gemini).

Guardrails for AI coding agents — scoped phases, reproducible proofs (exit 0 on the committed tree), and a bundled Multidim analysis engine. Pure Python, zero deps, local-first, Apache-2.0.

Open-source, local-first desktop AI client and MCP host. Bring your own key for Claude, GPT, Gemini, Ollama, or any OpenAI-compatible endpoint — conversations stay on your machine.

Differential harness that finds values a generated JSON Schema accepts but the runtime validator it came from rejects. Zero runtime dependencies. Works with Zod, Valibot, ArkType and TypeBox via three-line adapters.

Native Rust whole-codebase analysis for AI agents.

Valid tool calls from any local model — a drop-in OpenAI-compatible proxy for Ollama that guarantees well-formed tool calls and restores tool_choice.

Capable coding agents on local Ollama models — including the small ones. Task-based model routing, tolerant tool-call parsing, and an auditable permission system.

Yandex Search API plug-in for Hermes Agent

Code Turtle "🐢" is the open-source AI code review platform that helps teams ship better code with intelligent pull request reviews, inline feedback, and noise-free re-reviews 🚀

Free MCP server to convert, compress & merge PDFs and 100+ file formats (Word, Excel, images, ebooks) from Claude, Cursor, VS Code & any AI agent. Powered by GuruPDF.

Routed skill-design catalog for AI agents with one /skill-master command, npm scaffolding, validation, and cross-runtime guidance.

Keeps your agents in the loop about each other. See what the fleet is doing, then message, sync and send files between agents. Dibs reports; it never acts.

DeepSeek Harness Host Plugin: bili_summary Tool - Bilibili Video Metadata, Subtitle Timeline, Sharp Frame Synchronization Images, Error Handling and Degradation Built-in, Cross-platform Pure Node Implementation

LittleOrange Video MCP 是基于 Model Context Protocol (MCP) 的视频生成服务端，为 AI 应用提供统一、标准化的视频生成 API 调用能力。服务基于官方视频生成 API 文档封装，支持 Sora2、Veo3.1、Vidu Q3、Dreamina Seedance 2.0 等多个主流视频生成模型，内置智能异步轮询、三层工具架构（底层API映射、自动轮询工具、高层Agent工具）、完整素材管理等功能，完美适配各类 AI 客户端与 Agent 场景。

Local-first desktop app for building LLM test suites and running them against many local or cloud models at once

Local multi-protocol LLM API tester for OpenAI-compatible, Anthropic & Gemini endpoints · 本地多协议 API 测活工具

EcoHub AI is a full-stack outdoor social platform that helps users discover scenic spots worldwide, organize meetups, join outdoor communities, chat in real-time, and generate personalized travel plans — all powered by AI.

Check detected chart patterns against the rate the market moves that way anyway, so you can see which signals carry any information at all. Lift over a pattern-free baseline with cluster-robust intervals -- never against 50%.

MCP server for Pi-hole v6 API — supports multiple instances

Database-to-AI automation: reverse-engineer, package as REST microservice, connect to AI agents via MCP.

Answers "where should I submit this paper?" from cited soft metadata — reviewer culture, framing requirements, real word limits — instead of model recall. 399 curated journal entries, a 166,821-journal ISSN spine, and blanks where nobody actually knows.

Claude Code skill that diagnoses real PageSpeed Insights / Core Web Vitals problems (slow LCP, high TBT, poor CLS) on a live URL — works with or without an API key, on any site or framework.

The official Go library for the Steel API

检测中转站的 DeepSeek 是满血还是野鸡：用 DeepSeek Harness minimal 预设的首轮请求面做思维链行为指纹。支持 OpenAI / Anthropic / Responses 三种协议，零依赖，带网页界面。Detect downgraded or rebadged DeepSeek models behind API relays.

A small set of open tools that make Claude Code run better: better-opus-4.8, memory-palace, claude-setup-optimizer, context-forge.

Save and resume your LLM work. A local-first MCP server that turns a long chat into a versioned, resumable project state. Two commands: Savepoint. Resume.

211+ MCP servers for US government & public data (SEC, FRED, FDA, Census, BLS, EIA, CMS, NIH) — works with Claude Desktop, Cursor, any MCP client. No API key for most.

The personal AI that actually remembers what you teach it. Corrections become lessons + temporal-KG facts retrieved on every future answer; living dossiers distill 70+ monitors of news into durable understanding. Measured, not asserted. Fully local.

transformers safetensors qwen2 text-generation code codeqwen

Local A-share research, LLM decisioning, deterministic risk control, and daily simulation

Open-source financial research agent whose false-positive rate is measured, not assumed. Permutation tests, multiple-testing correction, and a published calibration study that found (and fixed) a 45% false-positive rate.

终端里的编码 agent：接任意 OpenAI 兼容模型，任务计划/子代理/长期记忆/断网沙盒

Access Google Gemini through a lightweight, cross-platform Electron desktop application.

transformers gguf ai-model-builder fine-tuned lora reallexi

Token_Saver_Nova: Dependency-free hooks and prompt rules that reduce token usage and cost in Claude Code agent sessions.

AI agent for market and audience research: web research with citations, document ingestion for RAG, audience/persona profiling — backed by real web-search and document APIs

Explain failed DeepSeek Harness agent runs locally, then produce a redacted recovery plan. No model required.

Spec in, verified diff out — an external harness that keeps every completion check outside the model.

A local, user-controlled safety boundary for AI-powered automation.

Multi-agent AI coding with a human merge gate — sandboxed git for agents, small reviewed diffs, your call on every merge. Works with Claude Code, Codex, or the API.

Official implementation of DoLQ, a multi-agent LLM framework for discovering physically plausible ODEs from observational data.

Production-shaped agentic AI customer support platform: LangGraph + Gemini agent, RAG over Chroma, MCP tool calling, JWT auth, RAGAS eval dashboard, Prometheus/Grafana observability.

Multi-agent orchestration for Orca, as code — LLM-authored plans that fan out worker agents.

Deterministic CI regression testing for policy drift across model-visible tools, semantic validation, SQL compilation, database containment, and result release.

Open, vendor-neutral continuity protocol for coding agents: persistent goals, recoverable state, verified work, and clean handoffs.

LLM-driven orbital free-flyer agents — extends NASA JPL OSR (bug fixed) to 6-DOF space ops. CW dynamics · ROSA · Ed25519 sovereign attestation · swarm coordination

AI agent for YouTube growth — VidIQ-style keyword/tag research, competitor channel analysis, video SEO, trend discovery, and channel analytics, powered by muapi.ai.

Curated 2026 conference papers on Claude Code and Codex CLI—benchmarks, methods, failures, exact models, and auditable evidence.

A personal assistant that runs on your own machine, does real work on it, and writes itself new abilities when the ones it has are not enough.

Local-first n8n workflow manager with visual graph viewer, REST API, CLI, and multi-server sync

A LangGraph agent that writes literature reviews from arXiv — every citation validated against its source chunk, and the retrieval strategy chosen by measured ablation rather than guessed.

基于 CrewAI 的团队级多租户智能体编排与管理平台，支持自然语言生成 Agent、多智能体流程编排及 Docker 一键部署。

Complete MCP server for the Langdock API - 35 tools, AutoGen multi-agent team

🐦 Your agent, perched on your inbox — a tiny Go daemon that runs a CLI coding agent on whitelisted incoming email and replies in-thread

Autonomous AI coding agent driven by Markdown config. DeepSeek-ready, CLI + WebUI, 45+ tools, self-hosted

DeepSeek Harness 的 Python 重实现：插件内核 + 事件溯源 + 五段工具管线 + wanter（water+ant）物理经验层——纯梯度 0% 逃逸 vs wanter 100%，路径复用 ≈30× 加速

Terminal agent harness built from a coding-agent foundation — plug in your own agent via YAML config

Full-chain software development agent system for Claude Code — 6 master agents, 25 sub-agents & 96 atomic skills covering product, dev, QA, testing, ops & security.

a demo plugin for a preset with builtin musescore wasm editor/preview engine for agent composing

Coding on a budget. Free. Cheap.Curated list of open-source tools, free-tier strategies, and local runtimes for cost-efficient AI- assisted coding. Covers LLM model selection, API gateway routing, token compression (up to 90% reduction), MCP context servers, agent quality guardrails, self-hosted inference, and pricing intelligence with grants.

Living research radar for Agentic RAG — latest papers, adaptive retrieval & search agents, skeptical notes, and field-level synthesis.

The terminal office — an Ink TUI where a real agent manager (oikonomos) runs sub-agent employees: animated floor, mail, task board, chat with the boss.

Understand a local media file (image/video/audio) from the command line — transcript + structured description as one JSON envelope, via an agentic CLI backend (agy/claude/codex).

Autonomous repository evolution engine: agent-driven refactors, documentation and technical-debt cleanup.

An agentic coding workspace that will not claim success it cannot prove — every change goes through the project's own verification before it is reported as done

Cogito: Computational framework employing a Syncretic Catalyst (synthesis) & rigorous Critique System (analysis) autonomously. Deeply accelerates your expert research on scientific literature via LLMs/ArXiv.

Autonomous native crash debugging for Qwen Code via DAP → MCP. CodeLLDB, crash dumps, runtime evidence and agentic verification.