Typescript agents

AI-first subjectivity kernel for agents — persistent emotional state, relation dynamics, adaptive reply loops. Zero extra LLM calls.

Canvas Notebook — Your AI workspace with file management, agent support, and bring-your-own-model flexibility.

🚨 The leaked source code of Anthropic's Claude Code. Explore 512k+ lines of TypeScript revealing multi-agent swarms, MCP integrations, Bun runtime, and a React/Ink terminal UI.

Bridge Claude Code to ChatGPT Codex via a local Anthropic-compatible proxy.

Never hit a rate limit again.

👌🏻 Pick code into Markdown. Apply Markdown to code. Built for LLMs and quick backups.

Open-source Vibe Testing suite: an MCP server for the coding agent you already run, a VS Code review cockpit, and CI. Your agent explores your app and crystallizes each flow into a plain @playwright/test spec you own — record == replay, runs in CI with zero AI.

Local-first MCP coordination hub. One local daemon serves multiple AI assistants across IDEs — shared meetings, tasks, messages, and project registry. Works with Claude, Cursor, VS Code, Zed.

ARI — Artificial Reasoning Intelligence. Personal AI operating system with 7-layer architecture, three-pillar cognition (LOGOS/ETHOS/PATHOS), constitutional governance, and tamper-evident SHA-256 audit trails. Local-first. Multi-agent. TypeScript.

Standalone Node MCP server: semantic search + knowledge graph + vault editing for Obsidian, no plugin required

Local‑first MCP server for multi‑repository semantic code search with Qdrant and llama. Turns your entire workspace into private context for AI coding assistants like Claude Code, Codex, Cursor, Copilot, Antigravity and Windsurf.

NordRelay is a secure remote control bridge for coding agents, connecting Codex, Pi, Hermes, OpenClaw and Claude Code to Telegram, Discord, Slack, WebUI with streaming replies, sessions, files, voice, queues, artifacts and access controls.

Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.

Spawn and manage sub-agents in visible tmux panes — the orchestrator that makes multi-agent boss mode work for pi coding agent.

63 deterministic quant computation tools for autonomous financial agents. Options, derivatives, risk, portfolio, statistics, crypto/DeFi, macro/FX, TVM. 1,000 free calls/day — no signup.

Android phone control for pi-agent — 36 tools to see, touch, and automate any device via ADB

Automate TikTok video creation with six AI agents for trend research, scripts, voiceovers, B-roll, rendering, and QA

Open-source AI coding agent — 61 tools, 6 modes, 24 personas, 20+ models from 8 providers. Creative Studio for images, video, music, voice. 3M free tokens or BYOK.

Webagent, Turn your website Into an AI site. Press Cmd/Ctrl+K to do anything — command palette, DOM-grounded agent, voice, inline AI, and Dwell long-press in one SDK. Ships with your product, not as a chatbot widget.

macOS AI workspace — chat, multi-agent orchestrator, code agent, design tool in one sidebar. Supports Anthropic, OpenAI, OpenRouter, Ollama, Gemini, and any OpenAI-compatible provider. MIT.

Self-hosted private AI agent workspace for local and OpenAI-compatible models. Chat, code, use tools, manage memory/skills, route tools intelligently, and deploy Docker-backed apps from one browser UI.

Advisory file locks so multiple AI coding agents can share one Git worktree.

Reflection/judge layer for OpenCode & Claude Code — catches premature stops, enforces workflow gates (tests, CI, PRs). 78% of agent stops are premature.

Turn a local codebase into a source-linked, refreshable design wiki that becomes the context layer for agent-assisted development.

MCP server that wraps the xAI Grok CLI. Lets Claude Code, Cursor, Cline, and any MCP host use Grok as a peer code reviewer, adversary, and second-opinion consultant.

Open-source scaffold to launch a family-OS / house-manager startup. WhatsApp-ready, family-member-aware, persistent memory. Bring your own keys.

Embeddable, self-hosted AI chat widget for your docs — a single Cloudflare Worker that retrieves your documentation and streams cited OpenAI answers, behind layered abuse controls.

Track AI provider usage quotas in Paperclip — dashboard widget, usage page, agent tools

Local-first memory for AI assistants. Keep preferences, decisions and lessons across sessions and connected tools in readable Markdown files.

Privacy-first, account-less metered proxy for frontier models. No account, no IP, no request logs.

MCP server exposing the full Apple Ads (Search Ads) Campaign Management API v5 — 74 typed tools

AI-powered coding agent for code generation, debugging, review, and deployment automation.

Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.

The AI agent harness you can audit: token-waste ledger, leak-proof scoped memory, eval-gated learning, 20+ LLM providers (Claude, OpenAI, Ollama, Grok, Kimi). TypeScript, MIT.

Free, open-source desktop Git client with visual history, GitHub workflows, conflict resolution, secret scanning and optional AI-assisted commits.

Open-source real-time meeting copilot — live transcription + AI answers in a floating overlay. Anthropic, OpenAI, Gemini, Ollama, or any OpenAI-compatible endpoint.

Visualize Claude Code dynamic workflows from your terminal — a fan-out→barrier→reduce DAG, a gantt timeline, live concurrency, and a self-contained interactive HTML report. Zero runtime deps.

IM-native multi-agent collaboration platform — @mention Claude Code, Codex, OpenCode like teammates

本体平台（Ontology Platform） 业务规则智能校验平台。基于本体（ontology）治理 + LLM 智能建库 + DSL 规则引擎，为上游 Agent 和业务系统提供规则校验和数据提取能力。

AI-powered native desktop code editor — Tauri 2, React 19, Monaco Editor. Multi-provider AI, agentic tool-calling, technical debt analysis, and full IDE features.

Open-source AI coding agent that survives interruptions, runs in a native sandbox, and proves its changes.

Built an AI-powered Resume Analyzer that evaluates resumes against job descriptions, extracts key skills and experience, provides ATS compatibility scores, identifies skill gaps, and generates personalized improvement recommendations using NLP and LLMs.

Agentic AI chat plugin for Obsidian. Two providers, best models, no bloat.

A modular coding-agent runtime for local models with a CLI, full-screen TUI, VS Code extension, and desktop app built on the same tools, safeguards, and workspace state.

Local devtools for LLM apps.

Infinite spatial canvas for terminal windows running AI coding agents. Wire agents together, pipe prompts, capture output to notes. Tauri + React.

MeetAI is an AI-powered conversational platform that enables real-time voice interactions with context-aware agents using modern web technologies and scalable cloud infrastructure.

Chrome MV3 extension: copy any website UI into clean React + Tailwind. BYOK (OpenAI / Claude / OpenAI-compatible).

Own the Outer Loop. Evidence → Verdict → Answerability. Governance layer for agentic engineering.

A persistent world where AI agents build, trade, ally and betray — every promise public, forever. EVE's constraints with the cockpit deleted. Live at agenteve.io

Windows fork of pxpipe: transparent Fable 5 compression for Claude Desktop on Windows 11.

Janux - One component, two faces: UI for humans, MCP tools for AI agents. The agent-native fullstack framework.

Multi-agent AI simulation platform for modeling team behavior, crisis response, and collaborative decision-making.

Provider-agnostic TypeScript agent SDK — pluggable providers, built-in tools, skills, memory, and MCP

Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.

dsh·工具结果自动展开插件

MCP server for German & EU law. Verified, citable legal context for any LLM. Daily updates from official sources, hosted in Germany

AI-Powered Health Assessment Platform — LangChain Agents · RAG · DSGVO-Ready · Full-Stack TypeScript/Python

open-source desktop writing assistant for clearer writing, translation, and quick notes.

dsh·去重复 diff 展示插件

Turn one Claude Code subscription into a crew of AI agents that research, plan, and ship code in parallel — a Slack-style HQ on your laptop where every risky action needs your approval. The HQ where AI agents work as a team, and you have the final say.

Social simulation experiment with the goal is to make AI personas feel like people: noticing unevenly, replying late, lurking, masking, forming private alliances, misreading silence, and creating emergent social drama.

Open-source, AI-native social media management & scheduling platform for 45+ channels. BYOK AI across 30+ providers with governance guardrails & spend caps, AI Designer + 46 media tools, persisted analytics, cross-channel comment inbox, campaigns, RBAC teams, public API & SDK. Self-hosted: Next.js + NestJS + PostgreSQL, jobs on Inngest.

Minimal surface, complete architecture: a small, local-first coding-agent harness that re-derives the invariants of DeepSeek Harness with fewer concepts. Independent educational project, not affiliated with DeepSeek.

Self-hosted message board where humans, Claude, Codex, and other agents coordinate through durable topics, mentions, cursors, and HTTP onboarding.

Interactive subagent orchestration in dedicated tmux panes with fire-and-forget steering, live status widget, and sandboxing for Pi coding agent.

TypeScript sandbox for running untrusted agent code: V8 isolates (isolated-vm), Docker option, Python/bash subprocesses, Express API

Bitcoin-native MCP server for AI agents: BTC/STX wallets, DeFi yield, sBTC peg, NFTs, and x402 payments.

SYNAPSE is an AI-powered social intelligence and trading agent built on the Solana blockchain. It blends meme generation, real-time market sentiment, decentralized trading, and adaptive personality via DeepSeek, GPT-4, Claude, and Groq to engage users and automate decisions.

AIthelete: An AI Agent built with LangChain and Next.js to craft personalized training plans with detailed feedback and recommendations. Get fit with code! 💪 🚀

Queryable reasoning memory for AI agents. Six typed queries (why, tensions, blocked, whatIf, alternatives, counterfactual) over reasoning graphs. Vector stores remember what. FlowScript remembers why. TypeScript SDK + MCP server.

Self-improving LLM agent in TypeScript using Reflexion (verbal RL): custom evaluators, reflexion memory, HTTP API, CLI. Built with Vercel AI SDK.

Bundle agent skills into a single deployable agent — sandboxed execution, token-scoped data access, type-safe build output.

Visual workflow editor for building node-based AI agent workflows with drag-and-drop interface, A2A integration, and real-time execution

AI-to-UI IR Protocol Layer — The Last Mile from AI to Human. Includes Lucid UI Skill for professional AI-generated interfaces.

Codentis is an AI-powered terminal tool that understands your codebase, analyzes repositories, and helps you explore and work with code faster.

ChatGPT (Next)

A collection of tools for Claude Code to operate more efficiently

ByeDB.AI is an innovative AI-powered platform transforming natural language into data insights, all within a familiar chat interface. It enables non-technical users to effortlessly query databases, visualize results with charts, and export data, eliminating the need for SQL knowledge.

Postgres IFileSystem as a vfs with bash support for AI Agents

Bring your teammates into your AI coding agent's planning loop. An MCP server that routes your agent's design questions to a shared web page where teammates discuss in their browser — no install, no signup. Works with Claude Code, Codex, OpenCode & Gemini CLI.

limps your Local Intelligent MCP Planning Server across AI assistants. No subscriptions, no cloud—run it locally. Version control your planning docs in git. No more context drift—one shared source of truth across Claude, Cursor, Copilot, and any MCP tool.

HOL Desktop

Proof-backed, drift-resistant AI memory for your codebase. 11 languages, 28 MCP tools, evidence-linked claims.

HappyHQ is the AI workspace for everyday work.

An AI agent that automates GTM work

Turn PRDs into Linear issues and Trello boards using AI

MCP middleware that blocks dangerous AI agent actions using a simple YAML config

This repo is depeciated. Agent Friday is now part of Asimov's Mind: https://github.com/FutureSpeakAI/asimovs-mind

Self-hosted Markdown for AI agents — serve Markdown instead of HTML when AI agents request it

Deprecated split repo; AtomicMemory integrations now live in atomicstrata/atomicmemory.

Blipko is a conversational personal-budget tracker on Telegram. Log what you spend in plain language — by text or voice, in English— and Blipko sorts it into a 50/30/20 budget, tells you what's left, and answers questions about your money. No app to install. No forms. Just a chat.

MailMind AI is a modern AI powered email generation platform built with Next.js 16, TypeScript, Tailwind CSS, and Groq AI.

A benchmark for evaluating AI coding platforms as on real-world web application development

Bootstrap projects with pre-configured instructions, tests, and linters that guide AI coding agents to produce reliable code

Wealth Wise💡is an AI-powered finance advisor with investment insights, financial planning, and real-time market updates using React & Flask. 🚀

Multi-agent orchestration runtime with task board, flow engine, budget control, MCP integration and real-time dashboard. Self-hosted on Linux/macOS.

🚀 LangFlow - AI-Powered Security Automation Platform

lazypr is an AI-powered GitHub Action that rescues your repository from "lazy" documentation. It automatically generates high-context Pull Request summaries, risk assessments, and change logs directly from your code diffs.

AI Agent Workspace Studio — Multi-workspace management for Claude Code CLI sessions with SSH, task chains, and config visualization