Search

Aggregate token usage & cost across all your AI coding agents (Hermes, Codex, Claude Code, Copilot, OpenCode, OpenClaw, Kimi)

Python routing library for local LLM agent loops: score prompts, map tiers to model names, embed in your runner.

Local privacy kernel for frontier LLMs — Gemma 4 E2B detects, redacts, and restores PII before any byte crosses the wire.

Halo host adapter for LangChain agents and LangGraph graphs (Python): a wrap_tool_call encode middleware plus a halo_fetch navigation tool. install_halo() wires it in one call.

AI model: mradermacher/Aether-1.5B-Agentic-core-GGUF

AI model: NadeemRazzak73/Qwen2.5-Coder-3B-Distilled-Agent

AI model: mradermacher/Agente-Llama-3.1-Asistant-16bit-v2-GGUF

AI model: senthil-kumar/qwen-linux-tool-use

AI model: fduliam/Qwen2.5-7B-Instruct-GRPO-ToolUse

Framework de game engine top-down em Pygame com NPC controlado por agente de IA generativa (Gemini)

No-code AI agent builder — turn one sentence into a single agent or a multi-agent team. The engine inside Agentlas. A no-code CrewAI / LangGraph / AutoGen alternative that runs on Claude Code, Codex, and Cursor.

Open-source platform for building teams of AI agents — orchestrator delegates, specialists execute, persistent memory learns. Multi-tenant, self-hostable on Postgres. 80+ AI providers behind one adapter.

Infinite Context AI Company — Graph Memory + Experience Engine. Corporate governance (red/blue debate, board review), dynamic worker pools, persistent cross-project memory. Gets better with every project. Deploy locally.

Local-first LLM operating-system hub for BACH, Rinnsal, gardener, SQLite agent memory, MCP servers, skills, and multi-agent orchestration

ATRI 是本地优先的 AI Agent 架构与音乐工作站，提供多模型 LLM Runtime、工具调用闭环、上下文压缩、子 Agent 并行调度、MCP/Skills 扩展。并融合 Web DAW、MIDI 工程编辑与 Rust 实时音频/VST 宿主，让 Agent 能直接读写工程、生成 MIDI、控制播放并协作创作。

Self-Improving LLM Agent for Puzzle Solving: This project presents the design and implementation of a self-improving Large Language Model (LLM) agent capable of solving logic-based puzzles through iterative reasoning, self-reflection, and adaptive behavior. The agent is evaluated on structured problem domains such as logical riddles, constraint-...

本地优先的个人 A 股研究决策工作台 · 案卷式研究闭环：进口判断→证伪→复盘→记忆。人做决策，AI 做广度/证伪/风险。A local-first personal A-share research OS.

Local-first, framework-agnostic debugger for LLM agents — see, replay, and diff what your agent did.

Game balancing framework using RL, MCTS, and LLM agents

Генерация User-Agent и HTTP-заголовков на ядре Go