Typescript agents

TUI for managing Claude Code plugins, MCP servers, agents, skills, and commands

opencode mac utility

A TypeScript-based autonomous agent framework with modular systems for memory, planning, and tool integration. Features vector-based recall, multi-strategy planning, and extensible tools for AI agent development.

Traceprompt is an open-source SDK that seals every LLM call and exports write-once, read-many (WORM) logs auditors trust.

🤝 Elevate collaboration with Claude Cowork, an open-source tool that enhances productivity through advanced AI capabilities for coding and digital tasks.

🛠️ Enhance programming workflows with a curated library of agent skills for tasks like code review, debugging, and planning for efficient project execution.

Elenchus MCP Server - Adversarial verification system for code review

your calendar, but yapping. Apple Calendar MCP server for Claude Desktop & Claude Code — 28 voices (Mom, Future-you, Garry Tan, LeBron James, Hilary Hahn, Alan Turing, Confucius, ...) yap on every event using your past calendar memory + web research. macOS-only, local-only, fully reversible.

One command. Your entire Claude Code setup. Done.

Transform TypeScript classes into JSON Schema definitions with automatic support for OpenAI, Anthropic, and Google Gemini function calling (tool) formats

Dynamic Intelligence Graph (DIG) MCP server for AI coding agents. Persistent code knowledge graph, a code RAG improvement, with hybrid Graph + Vector + BM25 retrieval, agent memory, multi-agent coordination, and impact-scoped test selection. Works with Claude Code, VS Code Copilot, and Cursor.

IntelliSearch is an advanced retrieval-based question-answering and recommendation system that leverages embeddings and a large language model (LLM) to provide accurate and relevant information to users.

[Experimental] Open-source RAG System for diverse document types

Snowflake-grounded natural-language chat agent over US Census data — guardrail → state resolver → hybrid metadata retrieval → structured plan + AST-validated SQL → self-check pipeline. Built as a 24-hour take-home in Next.js / TypeScript.

A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.

3D solar system explorer

Mindsage is an all offline journalling app

Curso completo de AI Engineer en español: 6 módulos / 16+ sesiones, TypeScript-first multi-provider, proyecto integrador real. MIT + CC BY 4.0.

[λ] Eigen - the platform to search your documents without limits

Stop writing resumes from scratch. EvidenceCV turns your real work into an ATS-optimized resume using RAG. 🥉 3rd Place - eHacks Hackathon 2026.

Token-efficient, layered context delivery for AI agents. Four memory tiers (Identity, Session, Experience, Archive) — context is always available, just collapsed by default.

Code search and session observability for coding agents. Hybrid BM25+semantic, optional cross-encoder rerank, self-bench on your own data. npm install -g @sivru/cli

Oryx — Integrate your application with Contextual AI agents seamlessly, from interface to proxy, fully customizable and unbranded.

Persistent semantic memory for AI agents — SQLite + FTS5 + vector hybrid search, optional Qdrant

Build your own paper grimoire: collect arXiv papers and ask in Japanese with citations.

detoks는 LLM 사용 방식을 재설계하여 토큰과 컨텍스트를 최적화하는 CLI 시스템입니다.

Based on RAG, this Obsidian plugin enables intelligent conversations directly within your notes.

DeskRoute is AI receptionist for appointment-based local businesses - real phone calls via LiveKit, Google Calendar bookings by voice, and an admin dashboard for escalations and call history.

基于electron+llamaindex开发的本地AI知识库客户端，支持一键部署Qwen3、DeepSeek-R1等模型

A chatbot for HealthWise Clinic that uses OpenAI and RAG for accurate responses, built with Next.js and Astra DB.

듀듀의 포트폴리오 입니다

A tool for automatically converting OpenAPI into Model Context Protocol (MCP) Server instance

LLM Wiki

TypeScript SDK for experimenting, testing, evaluating & monitoring LLM-powered applications - Parea AI (YC S23)

The quality gate for the MCP ecosystem. Spec compliance, security scanning, and performance benchmarks for MCP servers.

MCP server for Dokploy. Two tools up front, 524 generated procedures underneath. Real deploys, less schema tax.

OpenCode configuration files

Context-aware graphics API for Remotion - fetch illustrations, icons, doodles from 6 free sources. No API keys.

Playwright for AI Agents. Test what your agent DOES, not what it SAYS. YAML-first behavioral testing. Catch PII leaks, tool abuse, step explosions. 3200+ tests.

The open-source AI-native browser. Ghost agent browses, researches, and executes tasks autonomously. Built-in ad blocking, encrypted vault, DNS privacy. Zero telemetry.

Dual pi-agent runtime harness. Two agents (local + Cloudflare) negotiate, share state, and self-modify via a 5-message protocol.

Local MCP server that captures the why behind your code — domain knowledge for Claude, Cursor, Copilot, and any MCP agent.

A native terminal workspace with visual tmux/worktree management and AI agent awareness

✨ AI-powered Obsidian plugin — 20 tools, Magic Write, agentic loops, vault diagnostics. Claude actually touches your vault.

Vendor-neutral memory layer for AI agents. Give ChatGPT, Claude, Cursor, Gemini, and Grok shared persistent memory. TypeScript SDK, MCP server, REST API.

Nexus is a self-evolving market analysis AI. It started with 10 rules and one system prompt — and rewrites both every session.

Secure Node.js execution sandbox for AI. Allows coding agents & LLMs to dynamically run JavaScript, install NPM packages, and retrieve results, facilitating code generation, testing, and interactive assistance. MCP-compatible.

AI 驱动的聊天管理工具，智能检测话题、分析用户画像，轻松搞定 99 + 消息！

The AI-Native Workspace OS. Combines a built-in browser with local AI to read web context, bypass API limits via Zero-OAuth Ghost-Auth, and generate visual UI dashboards.

Intelligent RAG system with knowledge graphs. Processes documents → extracts entities & relationships → stores in Neo4j → enables semantic search & AI-powered Q&A with citations. 🔗 Where documents become knowledge graphs. Advanced RAG system that turns your files into an intelligent, queryable knowledge base.

FFT_nano: autonomous farm hand that runs on your farm, learns your operation, and texts you updates. No subscriptions. MIT licensed.

Autonomous AI-powered game testing platform that uses browser automation and LLMs to evaluate browser-based games through a four-phase pipeline: load validation, control discovery, gameplay exploration, and quality scoring.

TypeScript library providing persistent memory for AI agents — conversation history, long-term memory with vector search, and automatic fact extraction.

Professional AI consultancy toolkit with case studies, templates, and reference implementations

No longer maintained. Structured multi-agent orchestration experiments for Codex, Claude and OpenCode workflows.

Governance layer for AI coding agents — every action classified, gated, and cryptographically logged. 751 tests. 3 dependencies. Zero databases. #rai-verify-2026

Fully automated TDD pipeline for Claude Code. Tester, coder, reviewer — separated so the agent can't cheat

TUI multi-agent dashboard for Claude Code — dispatch N parallel agents on GitLab/GitHub issues in isolated git worktrees.

多智能体思维协作平台 — 让乔布斯、芒格、费曼同时为你思考。通过认知蒸馏重构卓越灵魂的思维模型与表达DNA。

A production-oriented, TypeScript multi-agent AI platform built on Google Genkit. The system composes Genkit flows, reusable tools, and independent A2A agents to support complex tasks such as research orchestration, code generation, and content editing.

Managing more agents is easier when they are just one phone tap away!

OmniBridge is an MCP server that gives AI agents an ephemeral, gVisor-isolated sandbox to run, test, and cryptographically prove their code works — before it ever reaches production.

AI-powered feedback widget for Next.js — users chat with AI, feedback becomes GitHub issues, an autonomous agent implements them, and the system learns from its own failures.

💬 Lightweight AlgoChat client for corvid-agent — GitHub Pages hosted

Universal AI agent — autonomous digital worker for any domain

A powerful framework for building and deploying Agentic Oracles on the IXO network. Built on LangGraph, Matrix, and NestJS, this framework enables developers to create intelligent oracles with secure communication, complex conversation flows, and automatic marketplace integration.

Local LLM fine-tuning and chat for Apple Silicon

This sample demonstrates how to deploy an Agentic AI architecture using AWS Fargate for Amazon ECS with AWS CDK. The sample features an AI Service that connects to multiple Model Context Protocol (MCP) servers to perform various actions

PirateBao is a TypeScript/Bun agent-skill package for terse pirate-speak AI coding replies that preserve technical detail while cutting filler, with hooks, compressor CLI, OpenCode/Codex/Claude/Gemini cargo, .bao validation, npmjs gates, and token eval checks.

Agentic AI boilerplate with FastAPI, LangGraph, React, and real-time streaming focus conversation-first UX

Suite of project management Claude skills - planner, analyst & manager

Agent is built with the help of Firecrawl for MCP tools, Gemini for LLM's.

Hoomanity is a Bun-powered ACP relay that lets you use your existing coding agents, or run your own local agents, from Slack, Telegram, and WhatsApp with persistent sessions and tool approvals.

CLI tool wrapping the full Rollbar API v1

Court of Agents is a fully autonomous, live-streamed courtroom simulation. AI agents with distinct skills, tools, and personas reenact the entire legal process, from case creation to verdict, using real-time avatars and procedural roleplay.

Plan. Work. Review. Learn. — A minimal disciplined agentic development framework.

Daily is an AI-powered task manager focused on productivity, minimalism, aesthetics, and day-to-day planning

Плагин OpenClaw для ВКонтакте

VS Code extension to track AI coding assistant usage and maintain code quality. Works with Copilot, Cursor, Claude Code & more. 100% private, local data.

💻 Build and manage multiple coding projects seamlessly with XCoding, a lightweight IDE designed for focus and efficiency.

Market intelligence dashboard for Counter-Strike 2 skins with real-time price tracking, portfolio management, and AI-powered market analysis. Built with Next.js 16, TypeScript, Prisma, and SQLite.

AI-powered healthcare consultation SaaS that enables users to receive medical guidance, analyze symptoms, and interact with an intelligent health assistant through a modern web platform.

LeanClaw is a high-efficiency, security-first AI assistant runtime built for fast local execution, low resource usage, and reliable automation through constrained tool access.

OpenClaw in 815 lines: a personal AI assistant where every capability is a Markdown file.

Universal AI-powered application foundry that transforms architectural documentation into complete, production-ready applications

React Recall makes it really easy for you and your AI Agents to read logs, trace flows, and recreate / fix bugs.

Multi-provider LLM pipeline + open benchmark measuring when each frontier model runs out of distinct ideas. 10 LLMs, 16× cost-per-unique-idea spread for the same shipped quality.

AI-powered code review companion for GitHub PRs

SkillSync MCP — security-gated skill management for Claude Code, OpenClaw, Cursor & Windsurf. 60+ threat pattern scanner.

Agency-grade Discord MCP server — multi-guild project routing, AI-native notifications, and DevOps workflows for Claude Code and other AI agents

중소기업 및 소형병원, 약국, 학원 등 소상공과 개인을 위한 개인정보를 쉽게 설명하는 MCP — 37개 도구와 개인정보 가이드 및 상담사례 2,202 chunks를 사용하여 어려운 개인정보를 쉽게 알려줌.

Enhanced fork of claude-context with stability fixes, improved sync, and better reliability for semantic code search

AI API key & subscription manager for Claude Code — your keys never touch the chat

MCP server for VK Ads — campaigns, targeting, budgets, statistics (Russia). Part of WWmcp — 46 MCP servers for emerging markets.

AI agent platform with 22 security controls. Signal + WebChat + Discord. Powered by Anthropic Claude.

An AI agent that lives in your terminal and codes for you.

Chat with Claude Code in WeChat. Use your Pro/Max subscription, no API key needed. 在微信里用 Claude Code，零额外成本。

Governance proxy for AI agents — per-agent budgets, cost tracking, loop detection, and policy enforcement. Agents never hold real API keys.