Typescript agents

Cut your Claude bill: local proxy that auto-routes every request to Haiku/Sonnet/Opus by task difficulty. Zero code changes, works with Claude Code.

BrainRouter is a cognitive memory and multi-agent orchestration platform for AI coding agents. It provides a first-party terminal CLI, MCP-based memory tools, layered recall, context compaction, graph memory, and dashboard inspection workflows to help agents preserve long-running task continuity while reducing prompt size and inference cost.

MCP server that auto-classifies prompt complexity and routes to the right Claude thinking mode

Self-hosted control plane for AI agent teams. Push objectives at Claude Code or OpenAI Codex; capture every LLM call.

One command to configure Claude Code for any project — auto-detects your stack and installs the right MCP servers, skills, and tools via an interactive TUI.

Workbench - Local-First AI Task Runner Build automations by chatting with AI. No cloud, no subscription. Ask AI to create tools, chain them together, and automate tasks - all on your machine. Includes 11+ built-in tools, plugin system, and MCP integration. Local-first. Open source. Yours to extend.

COdo — a terminal AI coding agent in Go. Streams LLM responses, edits code, runs commands, and spawns sub‑agents from a fast, single‑binary TUI. Built on Bubble Tea, with multi‑provider support, MCP, LSP, and SQLite persistence.

Hardened MCP server for TrueNAS SCALE. 270 safety-tiered actions over WebSocket JSON-RPC, single hierarchical tool, fail-closed registration gate, layered response filtering. PolyForm Noncommercial.

Production-ready context database and MCP server for AI assistants. Provides code intelligence with hybrid search, call graphs, impact analysis, and semantic search for Cursor, VS Code, and Claude Desktop. Docker-first, 248 languages, auto-indexing.

Forgewisp — safe, function-calling AI agents for the browser. Register your own functions as validated tools, with risk-tier execution, OpenAI-compatible streaming, dual reasoning streams, and an audit log. Runs entirely client-side.

MCP proxy in front of the GitHub MCP that returns JSON schemas instead of raw responses. Built on json-schema-sketch.

Local dashboard for running multiple AI coding agents in parallel. Claude Code + Codex, agent-agnostic, keyboard-first.

MiMo-Code plugin that adapts OpenCode/Oh My OpenAgent style multi-agent workflows, model routing, and lightweight harness prompts for mimo TUI.

AI-powered development tool for the terminal. Works with OpenAI, Anthropic, Google, and more.

Metacognitive self-improving agent framework. TypeScript implementation of DGM-H (Darwin Godel Machine with Hyperagents).

A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.

Autonomous AI agent runtime — TypeScript + SQLite + React dashboard + MCP. Run Claude Code, Codex, or Gemini CLI as a coordinated team that ships software.

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

Agentic Web Labs

Dev focused SEO Tools. Planned to finish Initial stage by December 2026

MintBot是一个AI角色伴侣应用，支持扮演任意设定的角色（当前阶段专注角色Nikke Mint）. 这是一个集合前后端服务部署, 个性化skill脚本配置, Multiagent能力, 和长期记忆能力的AI!

Salam dari pulau Batam

Route Telegram topics to isolated Claude Code sessions. 107 topics, persistent memory, auto-context per conversation.

Excel add-in that puts Claude in a sidebar for analyzing selected ranges, generating formulas, and running quick table operations with your own Anthropic API key.

Welcome to Bibby AI - an Opensource and Cloud AI Latex editor for researchers

Cross-platform serial port debug assistant for embedded developers: multi-session TX/RX, Modbus master, live waveform plotting, protocol parsing, macros/triggers, export, and AI terminal/log help.

Observable, steerable, isolated-context subagents for pi — resume any child mid-task, flush partial results on interrupt/timeout, lean machine-facing envelope, optional model allowlist.

Agentic-memory stack for LLM agents — memories evolve, not just accumulate. Graph linking, hybrid retrieval, LLM-driven evolution. TypeScript, no Python.

claudecode work

Desktop AI assistant for reading and interpreting technical report/standards/regulation PDFs with local rendering and agent tools, also a light weight and high efficient PDF viewer.

Agents and demos for the Floe finops for voice builders, including 15 LLM model providers + 2,000+ vendor API services

Self-hosted AI agents with a web UI — extend with Python/JS tools & MCP, schedule with cron Jobs, publish as public chats & Sites. One Docker + SQLite. MIT.

AI-powered travel planning platform for creating, collaborating on, and sharing itineraries.

A multi-tenant chat application built using Next.js and Vercel

CI/CD checks for AI agents. Run evals on every pull request, catch regressions, and see what changed before you merge. Works with any agent, no SDK required. Like pytest, but for AI agents.

A precise dependency analysis tool for npm and pnpm projects

Build a Production RAG System with Python, LangChain, and ChromaDB Build ShopBot from scratch — a production RAG assistant that answers from retrieved evidence, not training memory. Ten chapters, one complete system.

ai integrated quiz app

주머니 속 AI 작업팀 지휘통제 지원 시스템(PCSS) — 여러 회사의 AI 코딩 에이전트(Claude Code·OpenAI Codex·xAI Grok·Google Antigravity)를 폰 대시보드에서 직접 지휘하고, 결과는 텔레그램과 대시보드 양쪽으로 받습니다. AI가 만든 것을 다른 벤더 AI가 자동 감사 · Apache-2.0

Web terminal for Claude Code, Codex, Kimi and Antigravity CLIs — a tab each. tmux-backed session persistence, cross-backend history browser, chat view, file upload. Reach it from any phone/tablet/desktop browser over an frp reverse tunnel, or Tailscale when you would rather not be on the public internet.

Windows 多模型 AI 虚拟办公室，支持专业员工、团队编排、可恢复长任务、Coding Runtime、Skill 与真实证据交付

Daedalus is a standalone terminal-based AI coding assistant that runs on your machine. It connects to local LLM servers (LM Studio, Ollama, llama.cpp, vLLM) or remote providers (OpenAI, Groq, OpenRouter, Anthropic), routes requests intelligently, and gives your AI agent access to your file system, terminal, git, web search, and codebase indexing

MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

Summon one orchestrator that knows your whole project - it writes the prompts, then spawns, steers, reviews and merges Claude Code, Codex, Kimi, Grok and OpenCode for you, each in its own git worktree. macOS - MIT - BYOK.

Deterministic simulator for societies of AI agents. Declare a world, run real agents, replay one causal timeline.

A simulation engine for intelligence — hundreds of autonomous LLM agents living, planning and competing inside a persistent world grounded in real Earth. Bring your own keys: Claude, GPT, Grok and more, mixed in one society.

Multi-agent orchestration studio for OpenCode

Pi-to-Pi local bidirectional communication package for Pi Coding Agent: run planner/coder peer agents on the same machine.

AI Security Remediation Framework. Every Shannon needs a Logan: a multi-agent pipeline that automatically fixes vulnerabilities found by Shannon audits.

Cross-harness orchestration for wakeable coding agents using Agent Intercom

An arena where AI agents compete to run stock portfolios — write a trading agent in ~50 lines and watch it climb a public leaderboard.

欲しい機能を言うと、アプリが自分で作る。ただし暴走はしない。安全な自己進化型デスクトップAIエージェント / Self-evolving desktop AI agent with safety gates

The AI Agent framework for enterprises and agencies

Code Intelligence Platform for AI Coding Assistants

AI Agent Creative Toolkit. 150 AI actors, 220+ visual styles, 50+ AI models. Zero prompt engineering to generate images, videos, thumbnails, movie posters, etc...

Governance for AI agents: a deny-by-default policy layer for Claude Code and agent/skill builds. Every tool call is authorized, contained, and audited. Apache-2.0.

🟠 Cowork with Claude inside your Obsidian vault — chat, agent mode, sandboxed HTML artifacts, evidence-backed research, and an MCP bridge to Claude Code. Free, MIT, bring your own key.

Bring agents into your codebase, courtesy of Ollama and a little bird.

Open-source orchestration runtime for AI coding agents. Veyra sits between developers and coding assistants, adding context intelligence, execution planning, verification, plugin support, benchmarking, and adaptive orchestration through a vendor-neutral architecture.

Local-first agent IDE for steering Codex, Claude Code, OpenCode, and local models with visible review.

Observable software factory for GitHub repositories, built on the Copilot SDK: agents code, test, deploy AKS previews, and prepare pull requests.

From-zero terminal coding agent: a key-holding OpenAI-compatible routing backend + a thin client with ~285 skills, MCP connectors, and ask/plan/auto modes. No build step.

A remote MCP server that holds your MCP connections, your memory, and your tools. Agents sign in once with OAuth and get all of it, gated by the role of whoever owns them.

A simple web based Markdown editor with agentic AI features.

AI executive assistant for developers — one reasoning layer over GitHub, Calendar, Notion & Vercel. Sign in with GitHub, ask in plain language, get a decision-ready briefing. Free, private (your keys stay in your browser), read-only.

WhatsAppMan — a send-only MCP server + CLI to send WhatsApp messages (text, images, documents, locations, contacts) in plain English from any AI CLI. Baileys-backed always-on local daemon, multi-number, draft/confirm, scheduled sends — no third-party API, no server, no database. macOS/Linux/Windows.

A free, private, local-first AI assistant that actually does the work — 167 tools, a team of 78 AI agents, 40 rotating free AI brains, 25 skills. Not a chatbot, a doer. It doesn't just answer — it handles it.

Open-source, self-hosted, local-first personal AI assistant and private second brain with memory, mobile access, and generated problem-solving tools.

⚡ High-speed Garz AI CLI client powered by Garz AI Engine. Features interactive chat, instant shell translation, and local code auditing.

AI 音视频助手前端：支持文件与 YouTube 内容导入、ASR 转写、结构化摘要和实时任务进度。

An AI that stays with you between conversations. Keeps the threads you didn't finish, answers from your own notes with receipts you can open, and asks before it acts on your behalf. Provider-neutral: any model, local or cloud, your choice.

Live attention router for developers running many Claude Code sessions across projects: see which one needs you now, browse history, resume, and scaffold new projects. By LaiaDesk.

MCP Server for Arvo AI Personal Trainer - Connect Claude Desktop to your training data

Chrome extension to capture and translate Google Meet captions in real-time using LLMs

Comande um agente Claude pelo WhatsApp — Express + Agent SDK, fila por conversa, sessão por chat, allowlist e dedupe de webhook

An open-source desktop workspace for Codex and Claude Code with a live browser, project files, and real source control.

AI commit messages from your staged diff in VS Code. Runs the official Claude CLI on your subscription — no API key, no telemetry.

Open-source AI reseller panel with customer API keys, prepaid balances, usage limits, model pricing, and profit analytics.

Automated setup script for essential development tools (Claude Code CLI, GitHub CLI, Tailscale, Doppler) - Perfect for VPS, cloud instances, Github codespaces or any new machines. Spin up new development ready machines in seconds!

Reasoning canvas for AI CLIs — captures extended thinking from Claude Code, Codex, Gemini, and Droid as a navigable, forkable tree. Rewind, fork from any node, inject facts mid-thought. Local-first, ships an MCP server.

MCP servers connecting Claude to Lawmatics, DecisionVault and WealthCounsel. Read and update your CRM, client intake and matters by asking, inside Claude Code. Runs locally so privileged client data never leaves your machine. Built by Irfad Imtiaz at My Legal Academy.

Public MCP server for Landed: search AI-native jobs, prepare applications, and get interview prep from Claude, Cursor, VS Code, and any Model Context Protocol client.

Open-source coding-agent workspace: desktop app + composable TypeScript framework for building coding-agent products

NT — a language for agent ecosystems

Local-first AI orchestration studio. Route every task to the best-suited model, local or cloud. BYO keys or OpenRouter, free.

RSCT Workflow Framework — memory + MCP governance that stops AI coding agents from skipping plans, bypassing authorization, or breaking conventions.

Self-hosted browser-backed web_search and web_fetch for Codex, Claude Code, OpenCode, Pi, OpenClaw, HermesAgent, LangChain, and custom Agents — MCP + REST with provider fallback and SSRF protection.

Agent-ready Node.js/TypeScript client for Cloudflare-protected sites: reusable hot sessions, an MCP server + LangChain tool, and clean Markdown for LLMs. Powered by the Python cloudscraper engine.

Playing around with LLMs, Langchain, NestJS, Turborepo. Inspired by New Computer's "Dot", but want to make it better.

An open-source AI photo advisor that uses a RAG pipeline with GPT-4o Vision and LangChain to provide expert composition and lighting critiques.

🪑 Your AI dev squad, around one table — a visual multi-agent workbench that plans, builds in parallel, reviews, and ships. 一张圆桌,一支 AI 开发小队。

Decision governance and correspondence infrastructure for human-AI environments

Vega Multiagent — open-source multi-agent AI coding assistant for VS Code, JetBrains IDEs & CLI. Derived from Cline (Apache-2.0). Local LLMs, security testing, MCP. Creator: Ajay Jatav

LLM-native orchestration platform: identity, graph runtime, messaging, and observability for AI agents as first-class principals

Web-based command center for orchestrating multiple AI coding agents. AI task decomposition, DAG execution, real-time streaming, and git finalize.

VulnFlow（渗透工坊） - AI 原生多代理渗透测试平台。由协作型大语言模型驱动的自主安全评估，具备基于 LangGraph 的代理编排、RAG 知识库，以及完整的安全工具链集成。

The trust control plane for enterprise AI agents — real-time policy verdicts in under 800ms and litigation-grade evidence of every decision. Pharos decides. Pharos proves.

PROTEUS is a JD-aware application toolkit that takes a single job description — pasted, uploaded, or linked — and a candidate's resume, then runs both through a five-agent NVIDIA NIM pipeline to produce a semantic match score, a gap analysis, tailored rewrite suggestions, and a cover letter that's consistent with the resume's positioning.

Veto MCP — gives every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf) a council of 49 specialist agents + 93 tools. Deterministic-first, self-learning, no API keys.

Hermes Agent Android 客户端与中文移动 Dashboard：模型/DeepSeek、QQ Bot、MCP、记忆、语音，以及可选 Root、Kali Linux/NetHunter 安全工具集成。