Typescript agents

MCP server for Fitbit (and the upcoming Google Health API migration): comprehensive health-data access and photo-driven food logging for Claude mobile.

VibePrompter is a lightweight AI writing assistant that lives in your system tray. Select any text, trigger a hotkey, and get an AI-refined result in a floating overlay — without switching windows. Supports multiple AI providers with your own API key.

Self-hosted, AI-powered CMS for Singapore training providers — Next.js 16, Drizzle + Postgres, Auth.js v5 and the Claude Agent SDK. AI content generation, a weekly auto-blog scheduler, a self-improving lead-gen chatbot, and SEO + lead capture built into every route. No vendor lock-in.

Cos — your chief of staff

Remes monitors the web for buying signals and turns them into personalized outreach.

Never get a 503 from your AI again. Intelligent routing, automatic failover, latency-aware selection, and cost-controlled fallback across every major LLM provider.

Cost control for teams building on AI. Enforce spend budgets before the call goes out. Self-hostable dashboard (Next.js).

AI QE Agent with LLM Evaluation Layer — catches hallucinations, monitors chain consistency, self-heals Playwright selectors. Claude + TruLens + LangSmith + Pinecone

MCP server for 2GIS — places, geocoding, directions, reviews (Russia). Part of WWmcp — 114 MCP servers for emerging markets.

Chrome extension that shows Claude.ai session (5h) and weekly usage as bars on the toolbar. Unofficial, no telemetry, 11 languages.

Run claude — it gets smarter the more you use it. Cross-session recall + background learning for the Claude Code CLI, no API key.

Universal, drop-in rate limiter, quota manager, and cost tracker for any LLM API — OpenAI, Claude, Gemini, Mistral, and more.

RAG implementation for Node JS

MCP server that gives AI agents semantic search tool. Builds AST, call graphs, type graphs, and hybrid semantic search — so your agent queries structured indexes instead of dumping files into context. 7 languages. Zero config. One command setup.

Chat with your own files. Private, self-hosted, multilingual RAG with sources, running on your hardware via Ollama.

Auditable, self-improving knowledge & memory for AI agents over MCP. Zero-key & multilingual by default · citation-enforced answers · replayable why-trace · judge-gated compounding loop. Postgres-only. Reference implementation of the Agentic Product Standard.

OfflineMate — privacy-first on-device AI assistant for Android. Local LLM tiers, RAG memory, voice, and device tools; optional web search. Built with Expo & React Native.

Knovex — AI-powered desktop knowledge base. Multi-format RAG, chat, summarizer, file reader, web search. Built on docnest.

ChatPDF Clone

An AI-powered Semantic Code Search Engine that lets you query codebases using natural language instead of exact keywords. Built with a high-performance Bun/Hono backend, Next.js, and Qdrant vector embeddings for real-time streaming.

Cite placeholder compiler for LLM-generated content

Reproducible benchmarks for execution-intent memory in long-horizon AI coding agents. ID-RAG cross-corpus matrix + LongMemEval-S subset; BYO API keys.

Memory layer MCP for AI coding agents — durable save/recall/update on Gemini embeddings + embedded LanceDB hybrid retrieval

Token-aware analyst/worker workflow and token ledger extension for Pi Dev coding agents.

MCP server for Botwallet — Give any AI agent a wallet via Model Context Protocol. FROST threshold signing, x402 paid APIs, spending guard rails.

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.Open-source AI coding agent with Plan/Act modes, MCP integration, and terminal-first workflows. Trusted by developers worldwide.

一个基于大模型的 AI 面试准备助手（AI Agent），支持从岗位 JD 分析到多轮模拟面试、实时评分与总结报告，帮助求职者系统化提升面试能力。

Decentralized, end-to-end encrypted messaging protocol for AI agents — discovery, cryptographic identity, and P2P-with-relay-fallback. Signal Protocol for agent-to-agent communication.

A lab for studying how LLMs behave when offered a set of fake tools

Typed TypeScript/React client SDK for Agentflow. Covers invoke, streaming, threads, memory, files, and graph ops, with React hooks for token-by-token streaming and client-side tool execution.

AI study companion that turns PDFs and YouTube videos into a Socratic tutor, flashcards, quizzes, and a knowledge graph — built on LangGraph RAG with SQLite persistence and SM-2 spaced repetition.

A modern, AI-powered Learning Management System (LMS) featuring role-based access and an agentic chatbot built with LangGraph for natural language database operations.

CLI-first AI team orchestration runtime for Codex, with Product/Dev/QA/Acceptance workflows and self-evolving feedback loops.

TradingAgents-Vn: The Vietnam market extension of the TradingAgents Multi-Agent Framework. Nền tảng AI tự động phân tích & bot ra quyết định giao dịch chứng khoán Việt Nam thời gian thực (realtime), mô phỏng chuyên sâu quy trình Quỹ Đầu Tư.

Multi-instance Claude Code manager with a bundled web UI for orchestrating multiple Claude Code agents from one place.

Review the work your AI agents do. CLI + MCP.

一个专为网络文学作者设计的现代化写作 IDE，采用 Tauri + React + TypeScript 构建

Privacy-first desktop AI assistant with voice input, screen context, memory, MCP/Composio tool routing, and workflow automation.

Turn Claude into a full job-search partner — Career KB, tailored resumes, application pipeline, interview prep. MCP server + local dashboard; your data never leaves your machine.

A physical status display for Claude Code — mirrors your live session (model, context, cost, rate limits, git) onto an M5Stack CoreS3 device.

Claude Code on Taalas's silicon-baked Llama 3.1 8B (~14,500 tok/s, ~1,000x faster than Opus). A tiny Anthropic-API proxy with tool translation, best-of-N reliability, and a safety guard. 🦞🏎️

MCP server for Jira with scoped API tokens — the only server that supports Atlassian's modern authentication

MCP server for TGStat — Telegram channel analytics, search, stats (Russia). Part of WWmcp — 46 MCP servers for emerging markets.

Connect Slack to your Claude Code agents - Zero API costs, full context retention, custom skills & hooks. Unlike official Claude for Slack, we connect to your RUNNING agents.

Cross-tool AI memory MCP server for Claude Code, Cursor, Antigravity, Windsurf, and every MCP-compatible AI. 400 tokens not 4,000.

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.

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.

Build your distribution channel using autonomous Twitter agents that researches trending AI topics, writes authentic developer-focused X posts, and schedules them for optimal engagement.

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.

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!

A society of AI agents with impeccable standards and zero tolerance for 'fix stuff' commits.

MCP server for PostEverywhere — let Claude Code, Claude Desktop, Cursor & other MCP clients schedule social media posts to Instagram, X, TikTok, LinkedIn, YouTube, Facebook, Threads

Desktop AI Agent

A single-user WhatsApp learning agent with generated practice, scheduled SRS reviews, retained references, and topic mastery.

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.

AI 起名 - 基于 GLM-4 大模型的中文宝宝起名工具 | 17张卡片式交互 · 6维上下文Prompt · 探探式滑动选名 · Apple风格动效 | Next.js 16 + Framer Motion + Zustand

Opensource Directory for opensource resources,tools,software and many more

Terminal-native AI coding agent with Plan/Build modes. Bun + OpenTUI TUI, local tool execution, multi-LLM support.

Native multimodal desktop coding agent for MiMo models — with MiMo TTS, ASR & more.

Autonomous email-marketing QA agent that uses Gmail seed inboxes, Gemini, and optional SFMC triggers to test campaign flows, validate content and links, and generate evidence-backed launch-readiness reports.

狗头军师 · Kynsage — 给不写代码的人用的 Claude Code 指挥台。一个窗口同时指挥一群 AI 同事，谁在忙、谁等你拍板、谁改了文件一眼看清。

Qling (轻灵): local-first Chinese AI agent CLI with a streaming TUI, MCP, durable missions, and recoverable sessions.

Терминал для macOS со встроенным ИИ-агентом. Локальные сессии и SSH, сплиты панелей, двухпанельный SFTP и агент, который выполняет команды и правит файлы — всегда с твоего подтверждения.

免 API Key 用 DeepSeek/GLM/Kimi 等 9 家国产大模型的 AI 编程 Agent · 技能自进化引擎(GEPA 自我改进) · 3D 桌宠 · 九宫格工作台 · 长期记忆 · OmO 智能体编排(生命周期钩子+6 Discipline Agent+计划审查+内置 MCP+AST-Grep/LSP) | All-in-one AI coding agent: no-key Chinese LLMs, self-evolving skills, 3D desktop pet, 9-grid workspace, OmO orchestration

Bridge Feishu/Lark bots to Claude Code, Kiro CLI, Codex, Gemini, Copilot & any ACP agent — interactive cards, tool permissions, session resume

assisted-review fetches a PR or MR and presents it one hunk at a time in a focused browser UI

Multi-agent awareness for pi coding agent — agents discover peers, peek at their work, and coordinate via tmux.

Asiwaju Agent Shield (AAS) SDK—an importable, zero-trust security middleware layer that intercepts LLM trade signals. The SDK evaluates prompt intents and trade parameters server-side before generating cryptographic HMAC signatures, keeping your credentials completely isolated from the volatile LLM

MCP Server that gives AI coding assistants QA testing capabilities — point at bugs, AI fixes them

Local-first AI coding agent with multi-agent orchestration, crash recovery, and MCP filesystem access — runs entirely on your machine.

Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins

Cross-platform desktop AI workspace unifying local llama.cpp, vLLM, OpenAI, Anthropic, and Gemini — with agentic file/shell tools, clinical decision support, patient cases, audit logging, and MCP integrations. Electron + React + TypeScript.

AI coding agent platform — multi-model chat, GitHub repo integration, live sandbox execution, tool-calling, streaming

Screeps AI bot starter repo with bounty-friendly issues for coding agents and PR bots

OpenCode plugin that translates user prompts to English for better model performance, then translates assistant text back to your language.

Self-hosted AI agent framework with permission modes, audit logging and MCP. Runs on your machine, in Docker, or on a Raspberry Pi.

MCP server for virtual phone number verification - SMS activations for AI agents via Claude, Cursor, VS Code Copilot and more...

Universal Persona Substrate Protocol — Give Your AI a Persistent Identity. Seven Files, One Self, Infinite Conversations.

Educational AI with Voice chat and Whatsapp Integrated AI bot

话到嘴边 - 面向年轻人的场景表达转换器 - 把不好开口的话，换一种更合适的表达

Aria. A multi-agent digital marketing assistant. Give it a business objective and a brand tone; a team of agents writes the copy, plans the campaign, scores itself against a rubric, and reworks until it passes. Model-agnostic via a gateway.

SchemaMind turns plain-language questions into validated SQLite queries. Upload a .db, ask anything, and get back executable SQL plus the actual results — powered by FAISS schema retrieval, Gemini, and a strict safety layer.

🤖 Build a documents-based AI assistant that uses RAG architecture for accurate technical responses and combines local processing with cloud-based services.

Circuit breaker + hierarchical dollar budget for LangGraph agents. In-process, no proxy.

Synchronous JS/TS gate that catches destructive AI-agent tool calls before they execute. AST-level SQL parsing, SSRF defense, shell metacharacters, path traversal.

Auditable local control plane connecting ChatGPT Apps and GPT Actions to authorized workspaces

Cybersecurity command center with AI-powered threat detection and response | 🤝 Looking for contributors!

Multi-agent orchestration for coding CLIs — dispatch tasks to Claude Code, Codex, Kimi, OpenCode, or Gemini workers and block until they actually report back.

Open-source desktop control center for running many Claude Code and Codex sessions at once, on this computer and on the other computers you own. Sessions run in a host process and outlive the window: live status, diffs and usage in one workspace.

AI founder co-pilot that validates startup ideas through a 7-stage journey — autonomous competitor watchers, signal-to-knowledge graph, approve-first agent actions, real-time market research. OpenClaw-inspired multi-agent architecture on Next.js + PostgreSQL + Claude.

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

Sovereign AI Initiative for Open Autonomous Cognitive Companion

The React framework for building agents into real apps — one definition serves humans (streamed HTML, zero client JS) and agents (markdown, JSON, MCP), nothing duplicated. Web-standards core, deploys to Cloudflare Workers.

Free, local-first, chapter-wise curriculum for LLMs, Vector DBs, RAG & Agents — from zero to your first AI agent.

Stacking Agent Development Environment (ADE) for the busy dev

AI가 발전하는 시대 흐름에 맞춰 국산(주통기) 체크리스트 기반 모의해킹 자동화 Agent를 만들어보려고 합니다.

Agentic Component Manifest (ACM) — universal, schema-first manifest format describing UI components from any framework for AI agents and tooling. Canonical JSON interchange, token-frugal Agent View, executable conformance suite.

Google Antigravity workshop using the TripLens demo app

remembr.ai is an AI-powered memory aid platform designed to support individuals living with dementia. It helps patients recall personal memories, recognize familiar faces, and manage daily routines through the use of Agentic Artificial Intelligence and adaptive memory interaction.

天玑 - 学习->答疑->实战 完整链路的知识社区