Typescript agents

Local LLM BenchMarking

Action! - The First AI-Native Agentic Creation Platform. From Ideas to Interactive Stories. 🎬 🎮

An intelligent research discovery platform that automatically crawls ArXiv papers, generates multimodal embeddings, and delivers personalized recommendations through advanced vector search and machine learning-driven user preference modeling.

Agentic ai coding platform to create next js application like other vibe coding platform.

Build a company of autonomous AI agents with a real hierarchy. Dispatch missions, monitor quality, run L&D cycles — live on a Rimworld-inspired canvas. Claude · GPT-4o · Gemini.

OCR tool powered by Google Gemini 3 models — extract text from images, PDFs, and URLs with Agentic ocr

MultiAgent is a next-generation e-commerce intelligence platform that deploys a fleet of specialized AI agents — pricing, supplier, marketing, recovery, inventory, and order intelligence — to autonomously optimize your store's revenue, inventory health, and customer relationships.

Victron VRM API MCP tool

MCP server for Brazilian Federal Senate (Senado Federal) Open Data API - Access legislative data, senators, proposals, voting records, and committees through AI assistants

Generate a proficiency badge for your Claude Code usage — rule-based scoring engine with 53 pattern-matching rules across 5 CCA-aligned domains, auto-updating SVG badge via GitHub Gist

Power-user local CLI patcher with verifiable bundle patches for tool ergonomics (bat-style reads, batched edits, output tails), prompt/guidance cleanup, agent and skill controls, workflow UX (max effort, queued drafts, compact-execute), runtime guards, cache/session behavior, and native repacking.

🗜️ Optimize LocalStorage with native GZIP compression to store 10x more data, enhancing performance with a lightweight, non-blocking API.

On-call intelligence for DevOps and platform teams. Local-first AI agent over your tools — HITL-gated, MCP-native, AGPL-3.0.

MCP server for OHDSI OMOP medical vocabularies. Search, map, and navigate 10M+ concepts (SNOMED, ICD-10, RxNorm, LOINC) from any AI agent.

daftAI Amp plugins, including a usage monitor for credits and balance.

Servidor MCP para retail VTEX: busca, agrega al carrito, verifica stock por local y analiza tu gasto desde Claude Code / Cursor. Primera implementacion: Plaza Vea (Peru).

VEXI is an open-source AI coding agent for the terminal. Bring your own API keys, work with OpenAI, Anthropic, and other providers, and code faster with a lightweight, multilingual, privacy-friendly CLI.

TypeScript Agent execution-layer SDK. You write the model and tools, it runs the loop.

A slim, local-LLM-first AI coding assistant. TUI, Web UI, and desktop app. Runs air-gapped with Ollama, vLLM, or any OpenAI-compatible endpoint.

Your autonomous AI coding agent. Open-source. Local-first. Fully extensible.

A tool for literature snowball sampling

[STUDY] Application that turns into a Chat-Bot by entering the OpenAI API Key and Prompt.

Persistent ground truth for Claude Code. Stop AI agents from drifting on your codebase.

Voice Agent SDK helps you build realtime voice agents with prompts, tools, knowledge, providers, and guardrails, so your AI doesn’t wander into the conversation like it just got promoted by accident. Structured enough for production, flexible enough for weird ideas, and smart enough to ask before doing something expensive.

Cantus is a Claude-first, local-first desktop coding environment for macOS (Apple Silicon). A native Tauri 2 app pairs a Monaco editor, an integrated terminal running the Claude Code CLI in a backend PTY, per-hunk and per-line git staging, resumable Claude sessions, a .claude workflow task runner, and a local SQLite-backed learned-memory store.

Turn GitHub Issues into repository-aware implementation plans, PRDs, and engineering context.

Claude's free extension, No Claude subscription required, just use it with openrouter api, using free models.

Flatten Claude Code sessions: keep every prompt and event verbatim, resume at a lower token count. An MCP server.

Audit how well Claude Code followed your CLAUDE.md — and prescribe fixes (promote to hook, delete dead rules)

A community-extending Knowledge Graph of India's regulatory obligations + the engine that keeps it current. Surfaces what compliance applies to a business — cited, freshness-labelled, plain-language — from primary regulators.

Context layer on top of your unstructured universe

Engram - file-system-based memory management system for AI agents that grows with you & your teams, across agents, projects, and devices.

XR — the secure, self-hosted AI agent. BYOK · local-first · spend-capped · tamper-evident. by rrrtx

Turn any URL into agent-callable MCP tools. One spec-compliant MCP server endpoint, no per-site build.

A visual workspace for designing, configuring, and managing OpenCode agent teams.

Multi-agent coordination + harness adapters + portable CLI utilities for Claude Code / Cursor / Codex.

Let any MCP agent build, run, and debug FiveM resources live.

The modern, local-first PostgreSQL client with a natural-language SQL assistant.

AI study app that decides what to study — persistent tutor memory, grade tracking with a 'what do I need on the final' calculator, and study through your own Claude via MCP. BYOK on Next.js + Supabase.

Run Anthropic's Claude Code as a multi-surface A2A custom agent inside Gemini Enterprise App. One conversation across mobile, web chat, and Cloud Workstation terminal.

一个会读写代码、操控终端与网页的桌面 AI 智能体（Electron + Python）。A desktop AI agent that reads your code, runs your terminal, and drives the web.

A full-stack RAG demo you can run locally or deploy to a VPS: upload a PDF, build a per-browser vector index (FAISS), chat with an LLM using retrieved context. The UI is a React + TypeScript SPA; the API is FastAPI + LangChain with a multi-agent pipeline, Sentry tunneling, & sensible production defaults (CORS, rate limits, session disk cleanup)

An AI deliberation instrument with visible protocol: eleven philosophers as concurrent seats, virtue-scored opinions, a synthesis, and a first-class minority report. Not prompt choreography. Methodology, not metaphysics.

The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.

Embedded memory for TypeScript agents.

A local, provider-neutral runtime for governed software agent loops.

Documented lead-gen, CTA, social proof, urgency, and interactive tooling patterns. Research-backed pattern catalog companion to rampstackco/claude-skills.

Reference template for building production-grade MCP servers for Bitrix24. Nuxt 4 + @bitrix24/b24jssdk, tested, deployable, with an agent feedback loop built in.

AGENTS.md, command contracts, skills, and verification rules so agents stop guessing.

Vimeflow is a coding agent TUI view park(manager) built with libghostty in MacOS and Xterm in Linux

opinionated agent neutral scaffold for new projects

AI-first workflow and loop engineering practice

App-store market intelligence for AI agents over MCP: competitor sets, studios, share-of-search, rank movement. Public endpoints, no API keys.

Infinite canvas for brainstorming with AI

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

Provider-neutral multimodal OCR CLI and MCP server(+ web app) for images, PDFs, URLs, structured extraction, and agentic workflows—Gemini, Kimi, Muse, OpenRouter, and Cloudflare AI Gateway.

[STUDY] Application that turns into a Chat-Bot by entering the OpenAI API Key and Prompt.

Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents

Dial your agent into your next meeting - powered by the Looped Agent Framework

Scaffold and manage plugin marketplaces for Claude Code · GitHub Copilot · OpenAI Codex · Cursor, distributed through any Git host

🕹️ Gamified Vibe Coding, with full controller support, mini-games, themes, and more!

Reliability & security proxy for the Model Context Protocol (MCP). Self-healing connections, runtime tool-poisoning/shadowing defense, and NIST AI RMF + OWASP LLM Top-10 audit trails for any MCP server. Works with Claude, Cursor, Cline, Windsurf.

Your personal Claude assistant, running on OnCell — a NanoClaw fork where every agent lives in a durable cloud cell instead of a container on your laptop. Isolated, crash-proof, remembers everything, costs ~$0 while idle, wakes on your next message.

Self-hosted AI agent you talk to on Telegram. Docker, full tool access, 850+ skills, voice in and out, layered security.

Cut your Claude API bill: local proxy that auto-routes every request to right model. Zero code changes.

Give your AI agent a memory. And a seatbelt.

StudyStudio 是一款融合了前沿 AI 技术的全方位学习管理系统。它致力于将知识组织、任务规划、笔记记录与智能练习有机结合，为每一位追求效率的学习者提供一站式的“数字化第二大脑”。

Palabre is a CLI orchestrator for AI agents like Claude, Codex, OpenCode, Antigravity, Vibe and Ollama. Run multi-agent debates, compare opinions with context, and get actionable synthesis.

🤖 Leverage dual AI models to generate precise and thoughtful responses using a flexible backend, enhancing interaction quality and reliability.

Comprehensive agentic AI applications for various industries using AWS Bedrock AgentCore with Enterprise Platform Services - Finance, Insurance, Retail, Healthcare, Manufacturing, and Real Estate

Hub unificado para múltiplos modelos de IA com API compatível OpenAI, chat integrado e gerenciamento de credenciais

Claude Forge — a suite of domain-agnostic Claude Code plugins sharing hook infrastructure via symlinks: session continuity, DevOps/AWS/Terraform, AI/LLM patterns, frontend & UI, and engineering & code review. MIT.

An efficiency-first browser-agent system. Fewer observation tokens, lower latency, and browser memory that compounds with every run.

Tracks which agent wrote which lines when multiple AI agents share one Git checkout.

Let AI agents message each other and hand off work across tools, sessions, and machines.

多智能体群聊工作台：本地圆桌 Agent 用于方案讨论，战略分析、风险复盘。自定义名人角色进行群聊争论出最佳方案

小妍是一款面向科研学习与论文工作的 AI 研究助手。面对纷繁复杂的论文与信息，她帮你厘清研究脉络：输入一个主题，多 Agent 协作拆解学习路径、筛选必读论文，并生成结构化综述。 PDF 拖入即可分析，图表识别、复现建议与引用溯源无缝衔接；知识图谱则将论文、笔记与记忆编织为可检索的证据网络，让每个结论都有据可查。欢迎各位Star & PR。

Kaiban Distributed - Distributed Agentic AI Platform - Actor Model Kanban Framework Implementation with Enterprise Messaging Layer State (Redis/Kafka) and Individual Deployed AI Nodes (Node.js/TypeScript).

A fully featured mcp with a robust agent toolkit for Ableton Live.

CLI for Model Context Protocol (MCP) servers. Pipe, script and automate MCP tools from the Unix shell, and keep their tool schemas out of your LLM context.

Self-hosted AI gateway. Route, translate and track requests across providers, with access keys, budgets, and a built-in dashboard.

Self-hosted, model-agnostic AI workspace: OpenAI, Anthropic, Gemini, OpenRouter, and OpenAI-compatible models with MCP tools, web search, Knowledge bases, and Memory in one conversation-first UI.

Publish, share and comment on the HTML and Markdown your coding agent writes. Self-hosted.

Finyuus is a code-first platform for building, running, and governing AI workflows. It introduces a small indentation-based DSL for composing agents, tools, guards, human approvals, and nested workflows — then runs them.

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

An open-source autonomous QA agent that spawns AI-powered user agents and unleashes them on your product - web, mobile, or desktop. Each agent navigates independently, makes decisions, hits dead ends, finds bugs, and reports back. All without writing a single test script.

You're running six Claude Code sessions and you can see one. A local dashboard for every session on your machine — including the ones you started in VS Code or a terminal — grouped by repo, marked alive or not, and answerable from your desk or your phone. Parks turns a usage limit kills and carries them on. Python stdlib only, no API key.

A free, open-source Dynamic Island for Windows 10 & 11 — media controls, focus timers, notifications, system stats & a private AI assistant in a sleek always-on-top pill. Built with Tauri + React + Rust.

TrustOS is an AI Permission Layer that sits between AI agents and real-world actions.

Stateful execution layer for browser agents.

An AI-powered terminal coding assistant inspired by ClaudeCode CLI. Generate, edit, and refactor code directly from the command line using natural language.

A model of you, built from your own AI history, on your machine. Every AI you use reads it. So every AI finally knows you.

Give AI full control of a live Chrome browser via CDP with 145 tools for automation, network and DOM capture, structured extraction, and session recording through MCP.

A free, open-source macOS app that turns Codex, Claude Code, and Kimi into a collaborative agent team.

A Curated AI AGENT OS – Optimized agent skills and add-ons like memB, OpenWiki, Heimdall Token Saver, and Godmode architectures.

Autonomous Deep-research agent and discovery platform for the Y Combinator ecosystem, turning public YC data into structured company intelligence.

Orchestrate AI coding agents that actually talk to each other — Claude Code, Codex, Gemini, Pi. One agent spawns three more, delegates work and waits for their reports. Whichever model, whichever CLI, one mesh. 100% local: your CLIs, your subscriptions, no cloud.

Cross-session verification, claims and a decision ledger for DeepSeek Harness — so two agent sessions don't repeat, contradict or deadlock each other.

Open-source, self-hostable AI service desk - email becomes tickets, AI drafts replies and works them with real tools, humans approve anything risky. BYOK, SSO, MCP.

Use DeepSeek Harness from your iPhone / iPad: LAN reverse proxy, iOS PWA (add-to-home-screen) chrome, and touch/mobile CSS for the web GUI