Havuz

Reliable AI Skill + MCP toolkit for agent-driven desktop CAD automation.

Needle, küçük cihazlarda tool calling, structured extraction ve embedding çalıştırmayı hedefleyen kompakt bir model ve yazılım paketidir.

Neden yükseliyor · Küçük cihazlarda yerel tool calling ve extraction ihtiyacına odaklanması, 216 günde 12.730 yıldıza ulaşması ve son 28 gündeki 36 commit ile 15 farklı yazarın katkısı dikkat çekiyor. Yıldızlar ilginin göstergesi; model performansının bağımsız doğrulaması değil.

Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents

ReachAI企业级智能体开发平台：快速、安全完成已有业务系统智能化改造，让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise system

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind

apfel, Apple Silicon Mac’lerdeki Apple FoundationModels modelini CLI, interaktif chat ve OpenAI-compatible yerel server olarak sunar.

Neden yükseliyor · 6447 yıldız ve 187 günlük yaş dikkat çekici; yerel model erişimini CLI ve OpenAI-compatible arayüzlerle kolaylaştırması ilgiyi açıklayabilir. Ancak verilen ölçümler yükselişin nedenini kanıtlamıyor; son 28 günde 47 commit’e karşın yalnızca 2 farklı yazar görünmesi geliştirme katkısının dar olduğunu düşündürüyor.

Open-source AI agent framework for PHP. Tools, memory, security guards and a ReAct loop built in. Works with Laravel, Symfony, WordPress, Dr

Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

AgentDock, AI agents için yerel bilgisayarlar, sunucular ve container’larda MCP üzerinden kontrollü işlem yapma runtime’ı sunuyor.

Neden yükseliyor · 125 günde 1.100 yıldız ve son 28 günde 105 commit ile dikkat çekiyor; altı farklı yazarın katkısı da yakın dönem geliştirme etkinliğine işaret ediyor. AI agents’a gerçek makinelerde işlem yaptırma ve birden çok cihazı tek akışta birleştirme fikri güncel bir ihtiyaca yanıt veriyor; README’deki Trendshift rozeti tek başına benimsenme kanıtı sayılmaz.

Review what your agent changed and approve what it may do: React components for multi-file diff review and tool approvals that return a resu

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

Use your own DeepSeek web account through OpenAI & Anthropic-compatible APIs. FastAPI reverse proxy with tool calling, vision & streaming.

WPS Office 全家桶（文字/表格/演示/PDF）AI 助手：挂 OpenAI 兼容 / Anthropic / Codex 多家模型，AI 通过工具调用直接读写文档；支持生图、MCP、中英双语，覆盖 Windows / macOS / Linux（含国产系统）。

On-device AI agent for Android, tuned for free OpenRouter/Kilo models with automatic model/key fallback and rate-limit recovery. Tools: web

A lightweight terminal coding assistant with Claude Code-like workflow, tool loop, and TUI architecture, built for learning and experimentat

Hermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini.

A local AI agent built from scratch in Python with Ollama: conversation memory, system prompts, and multi-step tool calling.

🐳 whalegate — OpenAI-compatible gateway into DeepSeek web sessions (Rust): account pool, failover, SSE, native-style tool calling (tool_choi

A tiny async tool-calling agent framework

Local OpenCode-backed LLM gateway for OpenAI, Anthropic, Gemini, and Responses API-compatible tools, with streaming and tool/function callin

Measure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.

Drop-in OpenAI-compatible API gateway for Qwen AI models. Use your Qwen account (chat.qwen.ai) as a free AI API provider in any OpenAI-compa

MilkyAi at bilibili🥛| Video-to-Notes Email Service with RAG Customer Support & 38K Followers/Users on Bilibili | Python, PostgreSQL, RAG, A

Self-hosted AI chat platform with multi-step tool calls, persistent Python sandbox, RAG, and Deep Research. Supports Claude, GPT, Gemini and

Self-evolving AI agent in Rust. Single binary, 10 LLM providers, 30+ tools, 17 platform adapters. Zero dependencies.

Pie – free, open-source AI browser agent for Chrome. Reads pages & PDFs, fills forms, extracts data, automates tabs, hands off to Claude Cod

FreeTheAI: free AI API and open model marketplace. One OpenAI-compatible endpoint at api.freetheai.org/v1 with free models, paid plans, and

Remote access to multiple devices through one MCP, with shared Recall memory, Workflow data, and centralized device status.

Wiggle, Claude’ın kod çalıştırma ortamına benzediği iddia edilen araç ve paket setini Docker image olarak yerelde çalıştırmayı sağlar.

Neden yükseliyor · Claude’ın kod çalıştırma ortamının yerelde kullanılabilir bir kopyası olduğu iddiası ve beraberindeki araçlar ile skill dosyaları ilgi çekici. Ancak 23 günlük geçmiş, 91 yıldız, son 28 günde 7 commit ve tek farklı yazar, benimseme ya da sürdürülebilirlik konusunda güçlü kanıt oluşturmuyor.

Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, a

轻量、自托管的多入口 AI Agent 机器人｜QQ 官方 / OneBot 11 / NapCat / 微信｜Rust｜Memory / RAG / Todo / Tool Calling

A coding agent harness built specifically for Motif-3

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

OnDevice Local AI Studio — run LLMs on iPhone offline. SwiftUI workbench with MLX, llama.cpp, whisper.cpp, RAG, and authenticated OpenAI/Ant

Production-oriented Spring AI platform prototype for RAG, tool calling, async ingestion, JWT/RBAC, and observability.

600 KB WASM runtime for Cactus Compute's Needle AI tool-calling models, Needle 3, 2 and 1 from one build. Browser, Cloudflare Workers, Node.

基于 Spring AI 2.0 的生产级 ERP 智能助手｜Production-ready ERP AI assistant with RAG, Tool Calling, chat memory, dynamic SQL tools, multi-tenancy and E

AI inference gateway and control plane for multi-provider routing, policies, caching, tools, and observability.

TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.

学习 learn-claude-code 后的 PR Review Agent 实践项目：构建 Debate Council 多 Agent 审查、Tool Calling、结构化报告与 AI Judge 评估。

A framework for building intelligent agents

Official RollingGo Hotel Booking MCP Server. 2M+ hotels at wholesale rates, 40+ LLM compatible. Free unlimited calls for businesses & indivi

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs

An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loop. CLI, HTTP API, web dashboar

Multi-LLM trading harness.

A lightweight, general-purpose harness for tool-using LLM agents, fair benchmark evaluation, harness baselines, and personal assistant workf

Free unlimited Gemini API for any OpenAI-compatible app.

Provider-neutral bounded agent runtime for Android/JVM: controlled context (trust/priority/budgets), profile-scoped tools, OpenAI-compatible

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

Privacy and security guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and tool authorization