Havuz

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

Android SDK and MCP server: 157 tools for calendar, contacts, SMS, files, camera, sensors, notifications and UI automation, for on-device LL

Losslessly compress the tool output your AI agent sends the model, prove every value survived, and report the exact tokens removed. Run it a

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

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

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

Free unlimited Gemini API for any OpenAI-compatible app.

Macaw — on-device AI agent for macOS. 2.7B LFM2.5 fine-tune, MLX 4-bit, 97 macOS tools, no cloud.

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

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. F

Verified catalog of 300+ APIs and MCP servers with opinions and statistics so that AI agents can call after a one-time API key/OAuth setup.

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

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

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done cla

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

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

Run the native 284B-A13B DeepSeek-V4-Flash-0731 LLM locally on one laptop CPU: pure C, 8 GB RAM minimum, no GPU, best TPOT 0.892 s/token, re

The execution safety layer for AI agents.

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

An open-source, self-hosted social AI agent across QQ, Telegram, Feishu/Lark and personal clients, with persistent identity, long-term memor

The agent loop for Python. Your harness, any model.

Minimal Go agent framework for LLM tool-calling loops (v1.0, stable). Typed tools, parallel execution, three hooks, streaming progress, snap

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

The best model under 200B at near 10 token/s exact batch throughput on a single laptop CPU, with an automatic 8 GB RAM path. Native C, no GP

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

The fastest-growing AI community on Discord. Chat, earn, and build together. discord.gg/crow

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/L

Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstrea

Pure-Rust async runtime for LLM agents. Multi-provider (Anthropic/OpenAI/Ollama), tool-capable end-to-end, structured permissions, real MCP

A managed proxy gateway and compiler for AI agents. It takes noisy OpenAPI/MCP directories, compresses them in flat mode, saves tokens, and

Think only when the tool call looks unsure: confidence-gated reasoning for small local models. Code, BFCL results and paper.

Self-hosted AI gateway with a built-in dashboard. OpenAI-compatible API, multi-tenant, sandboxed code execution, MCP integrations, file stor

Use Ollama,OpenRouter, Gemini, cohere and moonshot ai with Codex plugins, MCP tools, tool_search and apply_patch. Use any plugin you want wi

Local agentic AI runtime optimized for CPU-only consumer hardware, tool use and efficient local inference.

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

Use GLM models in GitHub Copilot Chat with your own API key. Supports image input, tool calling, and streamed thinking.

Unofficial OpenAI-compatible bridge for Factory Droid

Agent tools from many descriptions in a single integration. Authorize operations, not just tool calls, and approve them when a human is requ

Use your Cursor subscription as an OpenAI-compatible API. Direct agent.v1 protocol — real tool_calls, streaming, multi-account. No cursor-ag

Faraday, the on-device AI voice agent for Android. Gemma 4 runs entirely on your phone: real voice conversation, long-term memory, and tools

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。

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

Add AI agents to your .NET app: your methods become tools with role checks and human confirmation. Use the ready-made chat widget in Blazor

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

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

Rust AI Agent framework with MCP support, extensible tools, streaming & multi-agent orchestration

Janux - One component, two faces: UI for humans, MCP tools for AI agents. The agent-native fullstack framework.

Kata builds the best AI agent for a subnet through open competition — so anyone can mine that subnet with a proven, optimized agent.

MIT-licensed agent framework for the AxisVela ecosystem: governed agent loop, model/tool/memory/event primitives, plugins, sandboxing, and p

Tiny engine, immense models — run large MoE LLMs (gpt-oss, Mixtral, Qwen3-MoE) on ordinary machines by streaming experts from disk. OpenAI-c