Havuz

DeepSeek ve uyumlu modellerle terminal, desktop, browser veya ACP destekli editör üzerinden kullanılabilen, uzun süre çalışan bir coding agent sunuyor.

Neden yükseliyor · 159 günde 35.720 yıldız ve son 28 günde 932 commit dikkat çekici ilgi ve geliştirme temposuna işaret ediyor; ancak aynı dönemde yalnızca 2 farklı yazar görünmesi, aktivitenin geniş bir katkıcı tabanına yayıldığını göstermiyor.

Apache Maka, agent görevlerini Desktop, TUI ve CLI üzerinden çalıştıran ve her adımı kalıcı bir event log içinde tutan bir agent workspace’tir.

Neden yükseliyor · 123 günlük bir repoda 5.665 yıldızın yanı sıra son 28 günde 769 commit ve 23 farklı yazar görülüyor; bu, ilgiyi tek başına yıldız sayısından daha iyi destekleyen güçlü bir aktivite sinyali. Apache Incubator bünyesinde olması ve benchmark sonuçlarıyla görev kayıtlarını yayımlama yaklaşımı da dikkat çekiyor; ancak bu ölçümlerin bağımsız doğrulama düzeyi verilen bilgilerden anlaşılamıyor.

An audit agent that proves whether a person's data is really gone: resolves identity across systems, judges state at the audit cutoff, finds

An autonomous agent that takes work, does work, gets paid, and gets better at it.

Harness-oriented agent system framework for production-grade LLM agent applications

飲食熱量日誌 App。核心思想：讓 LLM 負責辨識品名與份量自動拆項後輸出結構化 JSON，並在後端接上可以成長的資料庫；熱量一律來自可核對的資料並由程式計算，每個數字都查得到出處。設計決策參考食物辨識研究及相關論文，以 Claude Code（Opus 5.5）協作開發。原為

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside un

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new archi

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

AutoHarness: Automated Harness Engineering for AI Agents

Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in tool

Agent trace and tool-use safety evaluation lab.

从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter e

NEWTON: Agentic Planning for Physically Grounded Video Generation

Ultimate Multi-Agent OS for Autonomous AI NPCs 2026

The marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it,

Open-source, single-binary, self-hosted AI agent — your models and data stay on your machine. A coding agent on par with Claude Code and a p

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or clo

A procedural Agent Skill that teaches custom-provider models how to discover, use, verify, and recover from Claude Desktop/Cowork-style tool

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

The agent that evolves with you 𖤍

A really fast and lightweight harness for AI agents

A modular local AI agent built with Python and Ollama, featuring tool calling, memory, web search, document processing, embeddings, and RAG.

An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every c

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

Delta-MFP: counterfactual-replay failure diagnosis for local tool-use agents (FAGEN @ ICML 2026)

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

Official Repository for our paper: PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

开源桌面 AI Agent 与 CLI：长期记忆、多 Agent、实时语音；Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· Open-source desktop AI agent &

Is your CLI ready for AI agents? Automated checks to ensure optimum agentic CLI use: don't block agents, don't waste tokens, ensure safe use

A wallet of AI agents that use real tools and ask each other when a question isn't theirs. Runs on your computer; the model is your choice,

Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.

Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs

Native runtime, integrations, and reproducible packaging for BTL-3 and BTL-3 Compact

Control Ableton Live from Claude and any LLM. An MCP server built on Ableton's official Extensions SDK: one .ablx, no Remote Script, no Able

Pi agent for Android — sideload the APK and run a Pi coding agent on your phone. Single-APK, on-device Termux runtime, Claude Pro/Max OAuth,

[Archived] AAOSP, predecessor to JibarOS. Early experiment in OS-level on-device AI (MCP + local LLM on Android 15). See JibarOS for the act

A LangChain-powered multi-agent system with agent routing, skill routing, and execution harness.

Ben — an autonomous digital entity that lives on Crustocean

TSCG - Deterministic tool-schema compilation for LLM agents, including text-mode tool use without native tool calling and context-budget RAG

🪝 透明可控的 AI Agent 终端 | 状态机 · 多层记忆系统 · 沙箱防御 · 完整审计 · 多人设多技能