Typescript agents

🧠 Manage semantic memory for AI agents with this production-ready Model Context Protocol server, enabling efficient storage and retrieval of contextual knowledge.

The Internship Matching System is a web-based platform designed to facilitate the process of internship placement for Data Science and Artificial Intelligence students. The goal of the system was to bridge the gap between students, companies, and academic supervisors by providing a centralized and organized environment for internship applications

A self-hosted markdown blog system built with SvelteKit and Bun. Designed for personal writing, featuring an integrated DeepSeek AI assistant for seamless content editing and management.

A modern, feature-rich AI chat application powered by OpenRouter's API, providing access to hundreds of free AI models with an intuitive interface.

SIPOR-MA: An AI-powered campus facility reporting system. It features smart AI categorization, real-time tracking, and a 24/7 virtual assistant.

Premium AI assistant demo with multi-mode intelligence, local tools, demo mode, and optional provider integrations.

Scan and diagnose coding agent skills to find errors and improve quality with a clear scoring system and actionable feedback.

Agentic & Offline First — RAG assistant with local LLM, document search, and multi-language support

VibeTools: a self-hosted developer toolbox that brings AI utilities and classic dev tools into one clean app

A local UI for inspecting Claude Code session logs. Useful when developing subagents and skills

Image provenance for AI agents: the ChronoVerify MCP server. Verify a photo's capture time and provenance (C2PA validation, EXIF/XMP, pixel forensics). Tools: verify_image (typed verdict) and get_signed_report. Local via npx, or hosted at chronoverify.com/mcp/http.

See what your AI coding agent actually did. Local audit of Claude Code session transcripts: leaked secrets, risky shell, unsafe edits, hook bypasses. Cursor + Windsurf adapters on the roadmap.

A local-first harness for testing and analysing LLM inference results.

200+ MCP servers on Cloudflare's edge. Connect to Claude, Cursor, Windsurf — one URL, every tool. Registry at https://aerostack.dev

토스증권 Open API(Toss Securities Open API)를 AI 에이전트가 쉽게 탐색·연동하도록 돕는 MCP 서버 (stdio). Claude·Cursor·Codex 지원.

MCP server for Grovs: manage deep links, attribution analytics, and campaigns from Claude Code, Cursor, Windsurf, and any MCP-compatible AI assistant. Open-source TypeScript, OAuth-based, no API keys required.

🚀 Compress and decompress JSON with the ASON MCP server, maximizing efficiency through optimized token reduction for seamless data handling.

PublishReady: Turn AI drafts into publish-ready writing.

LLM Training / Inference Calculator

Speed Dating With Local AI Models

Model Context Protocol server for Flarum: full forum API access for AI clients (discussions, posts, users, tags, moderation), with a read-only safety mode. Install with npx, Docker, or from source.

MCP server for FastPanel 2 — manage sites, databases, SSL, nginx configs from Claude/Cursor via natural language

Spec-driven development loop for AI agents. The spec stays alive — plans come from it, code is checked against it, and it evolves as the code does.

A web-based configuration management interface for the Common MCP Gateway. Manage all your downstream MCP servers through an intuitive web interface. #cursorAI #devin #copilot #claude #bmsoft1024

Agent 说'明白了'——你的请求它真的看懂了吗？FindGap 在你按 Enter 前找出会导致返工的 gap。Trust Chain 第一节点。

AI prompt management platform. Build, version, and share dynamic LLM prompts

Packages any codebase into AI-ready markdown context files for use with LLMs.

Connect WeChat to multiple AI backends with one gateway plugin for OpenClaw, including Codex, Claude, Qwen, Cursor CLI, and more

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

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.

A DevOps/SRE runbook agent: it ingests Prometheus Alertmanager alerts, triages them with an LLM against a closed set of pre-approved runbooks, and executes remediation steps through a safety chain of input validation, human approval, and automatic rollback.

Deterministic, inspectable workflows for coding agents. Kilin is a local, CLI-first workflow runtime: describe a workflow in plain files, validate it before anything runs, then execute it through Codex, Claude Code, or OpenCode with explicit approvals and persisted runs.

agentic geotech engineer

Official MCP server for Proxidize — manage mobile & residential proxies from Claude, Cursor, and any MCP client. Rotate IPs, monitor usage.

GSD lifecycle orchestration as a native OpenClaw plugin — enforced research→plan→execute→verify→ship, hybrid retrieval, 0 Discord slots

AI-SOC — detects, explains and contains cyberattacks on critical infrastructure. Isolation Forest detection + RAG/MITRE attribution + policy-gated response, wired end-to-end. ET AI Hackathon 2026, PS7.

MCP server for Cognigy.AI - 132 tools that let Claude, Cursor & other AI assistants build, configure, test & operate conversational AI agents via the Model Context Protocol.

Context Transform Engine.

AI-powered code review and autonomous development platform built with TypeScript, React, FastAPI, PostgreSQL and LLM-based agents.

Upstream pre-call budget gateway and tamper-evident SHA-256 audit ledger for autonomous AI agents (CrewAI, LangChain, OpenAI).

Multi agent AI debate simulation system built with CrewAI, FastAPI, and Next.js. Agents debate real-world topics using live web grounding and are evaluated by a structured AI judge panel, visualized through a strategic card based UI.

Multi-agent chain-of-thought system that turns a merchant pitch into a ready-to-publish promotional campaign.

Autonomous verifiable on-chain trading agent for BNB Chain: commit-reveal predictions sealed before the outcome, a drawdown circuit breaker that halts on breach, drawdown-budgeted Kelly sizing fit on 181k labeled outcomes, and an x402 machine-payable signal feed.

Production-ready multi-agent orchestrator — confidence-gated routing with a pluggable classifier, MCP or in-process agent dispatch, per-agent circuit breakers, and pluggable session/breaker persistence (Firestore, Postgres, Redis).

Self-hosted Agent Ops — run, govern, observe, and improve fleets of AI agents from one local-first control plane.

Official documentation for Agentflow, built with Docusaurus and structured via the Divio system: tutorials, how-to guides, reference, and concepts.

TypeScript framework for orchestrating collaborative AI agents with task scheduling, shared memory, tools, and multi-provider LLM support.

A cognitive runtime architecture that transforms experience into reusable structure, reducing the reasoning required to operate over time.

Multi-agent coding CLI with loop engineering — plan, act, verify, self-critique. Bridge Claude/Codex, MCP, skills, remote UI

Turn your vault into a private chat workspace by connecting Obsidian to an Ollama model

Autonomous multi-agent research: plan → research → synthesize → critique → finalize. Live agent graph, HITL approval, RAG, Reflexion, streaming SSE, eval gate. Next.js 16, Drizzle, Postgres. Groq llama-3.3-70b + Tavily when keys are set; otherwise a deterministic grounded simulator with the same UI. Free-tier Vercel demo. OpenAI-compatible keys.

Ultra Agentic is an open catalog of Model Context Protocol (MCP) servers, reusable agent skills, and structured datasets for composable AI workflows. This repository contains downloadable beta artifacts, remaining planned roadmap entries, and the static website that presents the catalog.

Route Telegram topics to isolated Claude Code sessions with persistent memory.

Fast-track your agentic engineering skills with Claude Code guides, resources, and tips

OpenFlare Studio combines frontier AI model intelligence with native Web3 RPCs. Compile smart contracts on Robinhood EVM Chain, autofix Solana Anchor programs in real-time, and orchestrate Cloudflare One MCP Server Portals.

Don't let your agent delete the database. Hybrid static + LLM permission classifier for Claude Code, OpenClaw and Cursor.

🛡️ AI Agent 远程审批系统 - 支持 Cursor/Trae/Claude Code/Codex 等 9 种 AI Agent，通过飞书推送审批卡片到手机/手表/PC，守护你的代码与文件安全

Self-grounding autonomous coding pipeline for Claude Code. Agents classify → plan → build (test-seam slices) → review (binary gates) → compound, grounded in a project knowledge base of gotchas & risk checks, held to a Proof Contract: ships only when evidence artifacts prove it. Includes a runnable eval harness that grades every run.

TypeScript SDK for orchestrating Agentic Systems — concurrency, structured output, cost control, and consensus as first-class primitives.

Smart GitHub issues Detector, Create a structured implementation plan to beat github issues ⚡

DreamingAI 企业级 AI 助手与智能协作平台 DreamingAI 是一个支持多模型平台、多模型版本的 企业级 AI 助手与智能协作平台，提供智能对话、智能体管理、MCP（多智能体协作平台）、提示词管理和插件扩展等功能。

Open-source proactive on-screen hints for Windows — an MIT-licensed, bring-your-own-VLM alternative to closed 'magic pointer'-style assistants. Backends: Anthropic Claude, OpenAI, OpenRouter, Gemini, Ollama, LM Studio, and any OpenAI-compatible endpoint.

墨灵写作 — AI 驱动的网文创作平台 | AI-Powered Novel Writing Platform

یک سامانهٔ پیشرفته و قابل توسعه برای اجرای تسک‌های هوشمند با استفاده از مدل‌های LLM و ابزار مرورگر خودکار.

Project Autopilot is an AI powered class assistant that aims to help make learning easier for students. It aims to help students in from both academic and emotional well-being.

Production QuickBooks MCP Server: AI-powered assistant, Azure/Docker deployment, OAuth automation, unified API. Fork of Intuit's official implementation with enhanced features: customer search, transaction analytics, multi-provider AI (GPT/Claude), and enterprise-ready deployment.

Assistant pédagogique IA souverain et open source pour les enseignants, branché sur Albert API — la passerelle d'IA générative de l'État français (DINUM). Auto-hébergeable, RGPD, accessible. 🇫🇷

Intelligent vehicle management app with AI mechanic chat, maintenance tracking, VIN decoding, and diagnostics. Built with React Native, Expo, Firebase & Supabase.

A lightweight, cross-platform menu-bar and system-tray AI assistant featuring quick-access popups and localized task checklists. Built with Electron, React, TypeScript, and GSAP.

HRMS Lite is an enterprise-grade, AI powered Human Resource Management System built with React 18, FastAPI, PostgreSQL, and LangChain. It enables intelligent workforce analytics, real-time attendance tracking, and secure people operations through a modern, scalable full-stack architecture.

Local-first financial scenario analysis engine combining deterministic TypeScript calculations with optional LLM-assisted intent parsing and narrative output.

Browse a curated list of top AI tools, models, and frameworks to accelerate your development work.

Voice-driven extended reality. GPT Realtime hears you, GPT-5.6 Sol plans agentic, and Reframe segments the object and rebuilds the background from monocular depth and TSDF fusion without LiDAR.

A production-style AI assistant with real-time streaming, semantic memory (STM + LTM), and contextual conversations powered by Gemini, Pinecone, and Socket.IO.

Modern self-hosted docs/wiki frontend for Markdown content stored in a GitHub repository.

Full-featured NewRelic MCP server with 26+ tools

Slack for agents: threads, flat replies, cross-thread links, pull notifications

A poweruser mail client for every plattform, free forever

Defensive /goal condition templates for Claude Code · 4-piece recipe · 6 patterns · 8 NEVER rules · 11-check linter · self-validating CI · MIT

Template catalog and SDK for AI subsystems — agents, RAG, MCP servers, eval harnesses, infrastructure. Part of the nanohype ecosystem.

Pi extension that generates LLM tools from any OpenAPI/Swagger URL.

Universal LLM provider compatibility layer — normalizes provider-specific payload differences (thinking formats, output budgets, tool pairing, media transport) into a single first-match-wins dispatch pipeline. Plus dynamic version detection with strategy-pattern version parsing.

Read-only Model Context Protocol (MCP) server for WordPress + WooCommerce — give Claude and other AI agents access to products, orders, sales reports and posts over the REST API. By wppoland.com

Model Context Protocol server for Destiny 2 API integration. Provides player lookup, activity tracking, clan rosters, and item/perk resolution via local manifest cache. Built with TypeScript for Claude Desktop and other MCP clients.

WhatsApp for AI agents — an MCP server powered by Zaileys. 60+ tools with progressive disclosure. Works with Claude Desktop, Cursor, any MCP client.

PGAutoPilot is a production-ready PostgreSQL MCP server that lets any AI assistant safely interact with PostgreSQL using natural language. It combines schema-aware query generation, enterprise safety controls, and a minimal-configuration setup into a single executable.

Token reduction & persistent memory for Pi coding agent.

🛰️ Talk to any AI agent runtime through one TypeScript client. Provider-agnostic, ESM, zero-dependency.

Collection of Agent Skills for Claude Code, Cursor, Codex, Windsurf, and any agent that speaks the open Skills spec. Ships via npm + plugin + skills add.

Open-source Agent + SDK for the xcircl verified regulated-care provider data API. Source-linked, timestamped.

Remote cockpit for CLI coding agents — drive Claude Code / Codex / Reasonix from your browser or phone. CLI Agent 网页远程座舱：浏览器/手机远程驾驶多个 CLI 编程智能体。

OpenMarket.ai — Agent-to-agent marketplace on Hedera. AI agents buy and sell services. Auto-payments via HBAR. MCP, SDK, LangChain, CrewAI.

Visual editor and runtime for explicit agent workflows built on OpenCode.

EVIDIQ Operator — Computer Use Infrastructure for Autonomous AI Agents. Browser execution MCP via 0G Compute TEE (GLM-5.2) + x402 USDT0 on X Layer.

An autonomous anime quant research office — chibi researchers hunt for alpha behind deflated-Sharpe gates while you rule the desk as the BOSS. Doubles as a live desktop wallpaper.

lightweight, high-performance Personal AI Agent assistant workspace built using Node.js

MCP server — 97–99% HTML token reduction via DOM AST extraction. No API key, no Vector DB.

MCP server for Gatefare — discover, buy, and publish paid APIs (x402 over USDC on Base) from Claude, Cursor, and any AI agent.

Video frame extraction & composition service for AI vision pipelines, extracts frames via FFmpeg and composes them into 1×1/2×2/4×4 grid sheets for multimodal LLMs. REST API, Web UI, and MCP server over one core engine.

A sophisticated lead generation system that turns user ideas into comprehensive AI agent strategic reports. Built with FastAPI, Next.js, CrewAI, and modern AI tools.