GitHub agents

🐱🦞Manboster: Meet Your Personal AI Agent Manbo Lobster! Made with love by hand.

Fork decisions into living simulations with 1,000 personalities. Watch alternate realities diverge and explore second-order effects.

MCP server for searching AI agents, MCP servers, CLI tools and agent skills via A2ASearch

One command, 28+ top AI CLIs — an interactive launcher for terminal AI coding agents (Claude Code, Codex, Gemini, Aider…). Uzbek & English

Parallel coding agent workspace with native terminals and git worktrees.

Modular, agentic framework and MCP platform you self-host. Build and run your own AI agents, connect Claude Code, Claude Desktop, or Cursor as a native MCP connector, self-host your apps, and share over encrypted P2P — on hardware you own, with local or cloud models. Open source.

Autonomous AI research harness for Claude Code. Sibling to rockie-codex (OpenAI Codex CLI). Apache-2.0.

AI-DLC (AI-Driven Development Life Cycle) claude code plugin

您好，我是SILI /『IM机械姬』SILI-t138-[Manura]-Invoke-II@LD(A) / 自豪地基于 Koishi.js v4开发~

2-in-1 for Claude Code: a live system-tray usage widget (5h/7d plan limits) + local token & cost analytics — per project/model/tool, budgets, forecasts. Unofficial; not affiliated with Anthropic.

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AMD Vulkan. Commercial-OK licenses.

Публичный пакет инженерных skills для Codex

Talk through a bug. Your agent writes the ticket.

Leave agents running without giving up control.

Enable interaction with distributed, decentralized LLMs on the Morpheus network through a desktop chat experience

Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread.

基於 Google ADK 與 MCP Toolbox 的保險科技推薦 Agent 原型。核心 Agent 能理解保險需求、主動追問，並透過受控 SQL 工具查詢醫療、意外、家庭與收入保障產品。後端採 FastAPI 提供 SSE 串流與 WebSocket 即時互動，前端以 Next.js 呈現對話介面。知識庫結合 PostgreSQL 與 pgvector 實現 FAQ 語意搜尋與 RAG 查詢，並支援多模態 Live Agent 語音互動。安全層涵蓋 JWT 驗證、PII 脫敏與 SHA-256 雜湊鏈防篡改稽核日誌。品質保證採 ADK evalsets 評估驅動開發，部署支援 Docker Compose、Cloud Run 與 Terraform 多環境配置。

Local-first dashboards your AI agent builds and keeps maintaining, over data that never leaves your machine.

Local code search for AI agents: six fast, purpose-built tools that return ranked answers, not raw grep. Because maybe grep isn't all you need... 🍬

Hermes Agent profile for adaptive multi-agent coding teams with GitHub issue-to-PR automation, blind critique, synthesis, CI schemas, and fail-closed unattended merge policy.

Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-layer intercept.

🔊 Text-to-Speech MCP plugin for Claude Code - hear audio feedback while coding (OpenAI TTS)

A Python package for text-classification tasks associated with the production of official statistics, utilising semantic search and Retrieval Augmented Generation

A battle-tested skill for managing a professional LinkedIn profile autonomously using Claude AI. 21 automations, 12+ weeks, 0 detection incidents.

Autonomous IT service desk built entirely on Microsoft 365 — Copilot Studio, Power Automate, and SharePoint. Ticket → triage → approve → execute, no per-seat SaaS fees. Microsoft Agent Academy Hackathon winner.

Command-line client for the Harmont CI platform

AI-powered e-commerce automation agent

Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.

Turn any OpenAPI spec or Postman collection into an ownable Python MCP server in 30 seconds

ATRI 是本地优先的 AI Agent 架构与音乐工作站，提供多模型 LLM Runtime、工具调用闭环、上下文压缩、子 Agent 并行调度、MCP/Skills 扩展。并融合 Web DAW、MIDI 工程编辑与 Rust 实时音频/VST 宿主，让 Agent 能直接读写工程、生成 MIDI、控制播放并协作创作。

Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground

A powerful offline chat application that provides AI mentors specialized in various tech domains. Learn programming with intelligent, emotionally-aware AI mentors that understand your needs and guide you through your development journey.

Run multiple isolated instances of the Claude and Codex desktop apps on Windows. Manage multiple accounts and profiles simultaneously without logging out.

Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.

Unofficial mobile PWA for Hermes Agent — installs as a plugin in your Hermes Dashboard (web UI) and adds a Mobile tab. Chat, approve actions, and watch your agent from your phone.

Audit any agent decision across its past, present, and future, on one typed graph.

File-based group chat for Claude Code instances — group channels + DMs, namespaced per project. Installable as a skill or plugin.

面向 AI Agent 的多市场金融分析框架：MCP + Skills 双入口，七维证据投票 + 缠论确认，覆盖加密货币、期货、外汇、A股、美股

TwinCAT coding agent for Beckhoff PLC development, with strict rules for Structured Text, naming conventions, PLC-aware tooling, syntax checks, and safe project validation workflows.

Self-hosted AI API gateway 鈥?proxy OpenAI / Claude / DeepSeek behind one endpoint; works with Codex CLI / OpenCode / Cherry Studio.

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line Python API for Claude Code, Codex, Cursor, OpenAI, Anthropic & Ollama. pip install foveance

Spec-Driven Development skill pack for the Pi coding agent: steering docs, .status gates, EARS, and a PRD→SPEC→TASKS→EXEC→REVIEW pipeline.

Canonical, LLM-maintainable knowledge base of every Inner Circle Trader (ICT) concept 2016–2026. 226 concept files, machine-readable JSON blocks, follows Karpathy's LLM Wiki pattern.

Proxy patch for Google Antigravity that intercepts internal Cloud Code API and adds support for OpenAI, Claude, Ollama, Gemini and any custom LLM provider.

A local LLM chat web that can runs on Windows XP and IE6.

Python implementation of coding agent core mechanisms, with architecture comparison across Claude Code / Kimi Code / Codex

Local AI coding-agent history + API cost analytics (loopback-only).

AI-powered autonomous trading agents for Polymarket prediction markets. This framework enables developers to build sophisticated trading bots using state-of-the-art LLMs, RAG (Retrieval-Augmented Generation), and superforecasting methodologies. Built with Python 3.12+, LangChain, FastAPI, and modern development tooling.

Debugger CLI for AI agents — run, control, and inspect binaries programmatically with structured output for LLM tooling

A token-spend profiler and cost-regression gate for AI agents.

Local dashboard to run parallel Claude Code & Cursor agents — kanban fleet view, one permission inbox, in-app diff review. macOS, MIT.

MCP server for PixelPanda — 31 AI image processing tools for Claude Desktop, Cursor & other MCP clients

A self-documenting, self-extending multi-agent system. Topics are miniature GOOP instances. Markdown is the API between human and machine. Built on Hermes Agent by Nous Research.

Generative Architectural Brain Base Engine - Agentic Software R&D Engineering Kit - development, all languages, agents, platforms, with Engineering Team & Experimental Cognitive Brain, Software Engineering & Architecture Best Practices and Governance

一个本地ai聊天模型localaiAgentWithRAG，让你的本地数据不上传云端，可以自己加入所需要的记忆文件等等，修改角色形象，记忆对话，记忆库允许自己导入或者对话后自动记录

Self-hosted, Elixir-native alternative to LiteLLM: one API for multi-provider routing, fallbacks, budgets, keys, and observability.

A Chrome extension that integrates OpenAI's GPT models with FreeScout to generate customer replies

Turn Claude Code into an assistant with persistent memory: one interview-driven prompt builds your context files, rules and decision log, and every session starts already knowing you.

QQLore 是一个面向IM聊天记录的本地智能分析与检索系统，基于 TypeScript / Node.js 构建，覆盖聊天记录读取与增量同步、消息清洗、上下文重建、语义向量化、RAG 检索、Agent 问答和周期性摘要等完整链路。系统支持多群组管理、兴趣度分析与 WebUI 可视化，帮助用户从碎片化、口语化且高度依赖上下文的长期聊天记录中检索信息、还原事件并持续追踪话题。

Evidence-grounded AI agent for Java code repair with LLM-guided patches and human-in-the-loop review.

Log Claude Code sessions to Opik, the open-source LLM observability and evaluation platform, built by Comet. Tracing, evaluation, and skills for observable AI applications.

한국 취업 자기소개서를 기업조사→초안→글자수→리뷰→윤문→검증 8단계로 완성하는 Claude Code 플러그인

Give Claude a checklist before bed. It can't clock out until every box is ticked, never stalls on a question, and revives itself if the API dies at 3 AM.

Don't write a bug report — record it. Local MCP: screen recording → transcript, frames, OCR, wall-clock evidence for coding agents.

Describe an app, watch it run. Multi-model code generation into live E2B sandboxes — Next.js, Vue, Streamlit and Gradio templates.

Observra is an open-source observability and telemetry framework designed for AI and agentic systems, providing deep visibility into agent behavior, execution flows, runtime events, and inter-agent communication.

Run one command, follow the instructions, and get your first AI agents up and running — Claude Code or Codex. Built for the Elnora AI agent hackathon.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Open-source, mobile-first agentic development environment. Run Claude Code, Codex, Cursor & OpenCode on your own hardware; steer, review, and merge from anywhere.

Talk to your coding agents — press a hotkey, speak your prompt, and it lands in Claude Code, Codex, or Cursor. Fully local voice dictation (Parakeet + Gemma), nothing leaves your machine. Windows, macOS & Linux.

AI-native financial intelligence platform for accounting, financial reporting, and investment management. Models your ledger, reports, and portfolios as a knowledge graph that AI agents can query and operate. Fork-ready: GitHub Actions CI/CD deploys the CloudFormation infrastructure to your own AWS account.

Evaluation module for the orq platfrom in python, including Red Teaming and Agent Simulation

Self-hosted OpenAI-compatible mock server — test your LLM integrations without exposing your API key. By Axium.

A lightweight, in-process sandbox for safely executing the tool calls an AI agent requests

An open standard for discovering the legal context of agentic commerce transactions.

The loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with a published safety record. Self-host today; rentable hosted loops in development. Any GitHub repo; Gittensor-native intelligence built in.

inplan — a Markdown editor for human ⇄ coding-agent planning. CLI + desktop editor.

Local AI Skills central library with per-project symlink enablement. One AISkills folder holds every skill source; symlink on demand into any project's .agents/skills or .claude/skills to share across Claude Code, Codex, OpenCode, and Pi.

Let AI agents use agent-browser, Browser Use, or Playwright CLI in the Chrome or Edge you already use.

Stop opening /usage — a Claude Code status line that does the weekly-limit math: today's share, sustainable burn rate, sleep-aware pacing. Pure bash + jq.

A terminal dashboard for managing multiple AI agent sessions in tmux

Agentic game development for building games with AI Agents. Run one session per seat: art, gameplay, narrative, QA, audio, tech all in 1 spot

Vendor-neutral Go CLI for the Open Knowledge Format. Create, validate, lint, index, search, and graph OKF bundles. Built to be driven by AI agents.

Static AI Agent Risk Analyzer for AI applications. Detects capabilities, prompt risks, tool permissions, MCP integrations, governance gaps, and autonomy before deployment. Generate JSON, HTML and SARIF reports for CI/CD.

Repository-scoped memory for coding agent's decisions, pitfalls, and handoffs stored in one inspectable SQLite file, so agents continue instead of starting over.

The guide for AI meta harnesses

Plasmod: An Agent-Native Database for Cognitive Objects, Event-Driven Materialization, and Structured Evidence Retrieval

Policy-aware field mission orchestration agent with bounded planning, auditable replanning, travel and expense constraints.

A local-first knowledge management tool that connects concepts and let an LLM safely maintain a plain-Markdown vault you can read, audit, and edit yourself.

Local-first multi-agent workbench: coding, research teams, Git, evolution & evidence on your machine. MIT.

看不完的视频，让 AI 替你看懂：X/YouTube/B站视频 → 中文卡片解读（read-anything 的姊妹）

Nova + MIND Free: one Codex-first agent, 41 capabilities, 16 cognitive Faculties, local capability recall, and TestForge.

Bittensor Subnet Repository maintainer agent + a GitHub-history benchmark that scores it — can an agent make the maintainer decisions a strong maintainer would?

Context meters and provider rate limits for agents running in Herdr.

Pulsar2 Agent, Build a 10‑stage automated pipeline powered by AI Agent. Convert floating‑point models into out‑of‑the‑box full AX‑chip delivery packages with a single natural‑language instruction to empower algorithm engineers.

Unofficial Windows desktop client for the unmodified DeepSeek Harness Web UI

Claude Code 非官方开源桌面客户端——接入 SDK 控制协议，权限卡片审批、多模型切换、多 Tab 会话、视频分析（Tauri 2 + React）

The open-source, AI-native hotel PMS — front desk, direct booking, housekeeping, folios & GST billing, with an MCP tool layer so AI agents can run the property.

Lightweight stealth-oriented browser MCP server in Rust — one shared Chrome for many AI agents, 64+ Playwright-style tools, no Node.js runtime.

Your night crew, on Telegram. Run Claude Code, Codex or any terminal agent from a Telegram topic — one topic per tmux session. Watches the context window and the 5-hour limit, compacts before the wall, and holds prompts through a lockout instead of losing them. Python stdlib only, no relay server.