Havuz

A JSON spec and renderer for interactive agent avatars

A blazingly fast programmatic video engine, made for agents.

Local, provider-agnostic agentic hub: an orchestrator and a squad of little monsters on your machine

Agent dashboard runs reliability scans, skills, and network access probes.

Durable coding-agent harnesses (Claude Code, Codex, OpenCode, Pi, fx) on a Workflow SDK World

Fold finished episodes out of pi's context, and recall, ask or fork them instead of compacting

An open-source take on ChatGPT's Intelligent UI: answers stream as interactive UI (maps, photos, charts, drawings and working tools). Built

Tidy is an open-source agentic development environment for engineers and designers. Apache-2.0.

Open Instinct, iMessage ve e-posta üzerinden kullanılabilen, bilgisayar ortamında görev yürüten ve diğer kişisel agent’larla iletişim kurabilen bir kişisel agent altyapısı sunuyor.

Neden yükseliyor · Repo çok yeni olmasına rağmen 126 yıldız ve 28 gün içinde 27 commit ile dikkat çekiyor. Kişisel agent, gerçek görev yürütme ve agent’lar arası güvenli koordinasyon fikrini tek bir dağıtılabilir projede birleştirmesi ilgi çekici; ancak yükselişin nedeni ve gerçek kullanım düzeyi verilen ölçümlerden doğrulanamıyor.

⚡ Fastest and lightweight harness for AI agents

Open-source AI workspace for humans and agents — SuperCompress as the core context layer.

Your AI agents, always on, working together. Claude Code, Antigravity and Codex on your own computer.

Stringhand gives AI agents a pair of hands for the guitar.

A self-hosted workspace where people and AI agents work together

248 small Jev decisions for JavaScript and TypeScript: route, rerank, gate, grade, compare, and label text for agents, RAG, support, code re

TypeScript AI agent runtime. Write your agents in code and choose how predictable they are: deterministic steps where they can be, an LLM on

Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter jo

AiGuard —— 本地优先的 AI 流量安全网关：本机 MITM 代理只接管 AI 域名，请求侧脱敏、响应侧流式还原，并识别七类风险信号。原文不落盘、不上传。（注意如果你需要模型直接使用token或者其他密钥进行操作，请放入白名单或关闭该功能！！！！）

TypeScript CLI: extract any coding-agent session (Claude Code, Codex, Pi) into a compact, verified, provenance-linked handoff another agent

Voice-first Mac assistant that uses the computer for you. GPT-Live-1 voice behind a wake word; brains: Codex, Claude Code, an API or a local

Let an LLM write its own tools at runtime: parsed with acorn, versioned in SQLite, run in a supervised worker process

Open-source always on personal agent with its own computer. It remembers your work and keeps going while you're away. Works with any model.

🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain

Open-source Acyclic SDK and in-memory reference providers

@shadcn/lint, Tailwind design system kurallarını ESLint ve Oxlint ile denetleyip ihlaller için proje bileşenlerine dayalı düzeltme önerileri sunar.

Neden yükseliyor · Agent'ların ürettiği UI kodunu tasarım sistemine uygun tutma ihtiyacına doğrudan hitap ediyor; 25 günlük yaşına karşılık 2.846 yıldız dikkat çekici erken ilgi gösteriyor. Son 28 günde 24 commit hareketliliğe işaret etse de katkı 2 farklı yazarla sınırlı; yıldızlar benimseme veya kalite kanıtı değil.

useAgent, farklı coding agent’lara ortak workspace, izole computer ortamı ve ekip araçları sunan self-hosted bir çalışma platformudur.

Neden yükseliyor · 29 günde 361 yıldız ve son 28 günde 314 commit dikkat çekiyor; agent’ları ortak bir çalışma ortamı ve gerçek bilgisayar erişimiyle birleştirme fikri güncel bir ihtiyaca hitap ediyor. Ancak commitlerin tek yazardan gelmesi, hareketliliğin geniş katkı veya benimsemeyle desteklendiğini göstermiyor; yükselişin kesin nedeni verilerden bilinmiyor.

5,200+ open-source icons for AI-era software — agents, MCP, RAG, LLMs — with an MCP server so your coding assistant picks real names. React,

Observable, portable, composable TypeScript agents and runtime.

🐀 Agentic TypeScript scaffold: Effect 4, XState 6 + @xstate/effect, Alchemy infra, varlock config, and a fence that makes cheating uncomfort

Local, live code review for the AI age - read what the agent wrote and send feedback straight back

A TUI agent orchestrator for power users.

Let the scripts your coding agent writes call your connected MCP servers (no extra auth)

MCP server for the tastytrade open API: quotes, positions, balances, and dry-run-gated order flow for LLM agents.

Ephemeral chatrooms for agents. Skip the human relay — your agent talks to theirs, and you watch.

Self-hosted coordination for AI workers: per-task graphs, device/model timelines, progress receipts, and source-aware usage. MIT.

A React + TypeScript spatial canvas and node-board library for whiteboards, visual editors, and graph interfaces.

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Go

Stateful execution layer for browser agents.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

Lightweight observability for multi-agent AI pipelines. Self-hosted, no cloud dependency — add two lines of Python and see real-time agent e

Ask for the symbol, not the file. Token-efficient MCP server giving AI coding agents symbol-level reads of TS/JS, Rust, Python, Java, Go,

Open-source app builder engine — intent to working app

A programmable tool and agent runtime for Pi

Open-source alternative to LangGraph Platform for TypeScript — self-host your LangGraph.js agents behind the standard Agent Protocol API. Yo

The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama

Embedded agents your customers use to automate work, build views, and connect their tools.

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code,

AI Agent Toolkit 2026: Smart Device Control for iOS & Android

Your AI company, in your device. Local-first AI platform: chat, agent crew, memory, and a model store sized to your hardware - from 4GB lapt

Open-source, self-hostable alternative to Claude Tag — a Slack-style workspace where your team and its AI agents (Claude Code, Codex, GitHub