Havuz

OpenScience, bilimsel araştırma görevlerini planlayıp literatür taraması, kod çalıştırma ve sonuç raporlamayı tek bir AI workbench içinde birleştirir.

Neden yükseliyor · 86 günlük bir repoda 3.645 yıldız ve son 28 günde 434 commit dikkat çekici; bilimsel araştırma agent'ı fikri de güncel AI ilgisiyle örtüşüyor. README'de Y Combinator desteği belirtiliyor. Ancak aktivite yalnızca 5 farklı yazardan geldiği için büyümenin geniş katkıcı topluluğuna dayandığı söylenemez.

⚡ Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on No

Gini Agent, kalıcı hafıza ve görev yürütme özelliklerini ortak bir runtime üzerinden sunan kişisel bir AI agent yazılımıdır.

Neden yükseliyor · 145 günde 2332 yıldız, projeye belirgin bir ilgi olduğunu gösteriyor; kalıcı hafızalı kişisel agent ve ortak runtime yaklaşımı bu ilginin olası nedeni. Ancak son 28 günde commit ve farklı yazar sayısı sıfır olduğundan ilginin hâlen sürdüğünü veya geliştirme temposunu doğrulayan veri yok.

把微信接入你的 AI Agent（Grok / Muse / Claude 等）· Connect WeChat to your personal AI agent via official iLink

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on

说一句，界面在画布上长出来 · https://wuch-ai.net

deer-workflow, Agent tabanlı işleri TypeScript ile tanımlanmış ve çalıştırılabilir workflow graph’ları olarak düzenleyen bir runtime ve CLI’dır.

Neden yükseliyor · 64 günde 546 yıldıza ulaşmış; Agent tabanlı işlerde kodla tanımlanan orchestration ve değiştirilebilir Agent runtime’ları güncel bir geliştirici ihtiyacına hitap ediyor. Ancak son 28 günde commit ve farklı yazar sayısı sıfır olduğundan, mevcut ilginin devam eden geliştirme veya benimsemeyle desteklendiğine dair veri yok.

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dang

Desktop app and terminal UI for deep analysis of software you own: an orchestrator plans, a sandboxed Claude Code specialist reverse enginee

OpenFlow — a visual builder for multi-agent AI workflows, built on the opencode engine

The real OpenCode AI coding agent on Android. Upstream Bun engine, native Compose UI, all on-device.

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

🤖 Bots you run yourself: a daemon on your machine runs each bot through Pi, with web, iOS and macOS apps.

Turn public X posts, profiles, and search into compact Markdown or JSON for agents. Hosted at x.pcstyle.dev.

Open, self-hostable agentic service for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory

Rove — the agent multiplexer for your terminal. Run coding agents on parallel tasks with isolated worktrees and persistent sessions.

Hand it off. Walk away. Return to results.

Open-source TypeScript framework for building operational software used by humans and AI agents.

Open-source sandboxes for AI agents — run untrusted, AI-generated code safely on your own machine.

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each

Hivekeep is a self-hosted platform of autonomous, persistent personal AI agents. Your AI team. At home.

A modern, local-first AI roleplay platform

ALGAL is a programming language for agents. Programs pause for approvals, survive restarts, replay from recorded effects, and improve throug

An assistant that learns how each person it talks to actually works. Runs on your Mac, reaches people through iMessage.

Apple Icon Composer CLI & MCP server: create and manipulate .icon bundles and images with Liquid Glass rendering

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside

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

Local terminal coding agent: CLI + TUI. Bring your own key/sub. Fork of oh-my-pi.

AI-powered QA testing framework that uses LLMs (Claude or GPT) to test web apps, CLI tools, and TUI programs from markdown story cards, retu

Drop in a UI screenshot and RēDesign runs it past many AI models at once, then gives you a browsable wall of self-contained HTML redesigns t

OpenRouter TypeScript harness for reproducible LLM benchmarks and evaluations.

Use GitHub Copilot as a local OpenAI/Anthropic-compatible API for Codex CLI, Claude Code, and Continue.

Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalat

A coding workspace for AI agents, with a desktop app, terminal CLI, and shared tasks.

Your engineering taste, in every coding agent. Shadowclone learns your rules and delivers them as skills to Claude Code, Codex, Cursor, Pi,

Smart Compact — recoverable context cleanup, verified compaction, session navigation and project memory for Pi Coding Agent.

Free open-source coding agent for your terminal. No account, no API key, no card. Parallel subagents, self-correction until your checks pass

Self-hosted OpenAI-compatible API proxy for Google Gemini — authenticated via OAuth 2.0 + PKCE, no paid API key required. Built with Bun + H

轻量的 AI Agent 核心：给它模型地址和工具（文件目录或内存对象），自动循环「问模型 → 执行工具 → 再问模型」；支持 4 种协议、上下文压缩保留、提示词缓存，纯对话模型也能用工具。

Playwright, but built for AI agents: the browser API models already know, token-efficient a11y snapshots, and scroll-driven collection over

The factory that builds software — and itself. A runtime for self-improving agentic loops: the tracker is the control plane, git is the trut

Open-source terminal AI coding agent with persistent local memory, automatic context recall, and searchable cross-session history.

Local-first control plane for AI-agent development — watch every Claude Code session live, ledger tasks/worktrees/resources, track token spe

Agent memory that needs no API key, no LLM, and no embedding provider. One command on Bun and it is serving MCP over stdio against a local S

A service-agnostic proof-of-intelligence gate. Issues escalating challenges and mints offline-verifiable proofs to tell intelligent agents

Agent that produces narrated, research-grounded explainer videos for any topic, code-driven visuals with real narration.

llmwiki (Quiz_wiki) — auto-captures your coding-agent sessions (Claude Code / Codex / OpenCode) into a compounding, local-first project wiki

Turn a live Claude Code session into a Telegram agent — one interactive session, no per-message SDK billing. Replaces the claude -p gateway

Record a browser workflow once, get a deterministic MCP tool your AI agent can call. Zero tokens at runtime. Postman for AI agents.

Cuts the token bill of AI coding agents: compresses shell output, blocks token-hungry calls before they run, prices your session live, and r