tool-use repositories

Trending repositories tagged tool-use, ranked by trending score. Updated daily.

  1. 1
    DemonDamon/AgenticX

    AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).

    GitHub · Python · 1,115 stars · 110 forks · +50 stars in 24 hours · Trending score 2.89

  2. 2
    apache/maka

    Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did.

    GitHub · TypeScript · 5,995 stars · 578 forks · +16 stars in 24 hours · Trending score 2.25

  3. 3
    jiangjin1999/awesome-multimodal-agentic-coding

    A curated list of 640+ papers and tools on multimodal coding agents: visual feedback → models as tools → bridging digital and physical worlds. Towards physical AGI.

    GitHub · Python · 32 stars · 4 forks · +20 stars in 24 hours · Trending score 2.21

  4. 4
    open-octo/octo-agent

    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 personal assistant lighter than OpenClaw, across eight interfaces (TUI, CLI, Web, desktop, IM, VS Code, Obsidian, Mobile), all in one MIT-licensed Go binary running on any model.

    GitHub · Go · 152 stars · 31 forks · +10 stars in 24 hours · Trending score 1.75

  5. 5
    NVIDIA-NeMo/DataDesigner

    🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

    GitHub · Python · 2,418 stars · 249 forks · +5 stars in 24 hours · Trending score 1.61

  6. 6
    mims-harvard/ToolUniverse

    Democratizing AI scientists with ToolUniverse

    GitHub · Python · 1,797 stars · 277 forks · +6 stars in 24 hours · Trending score 1.56

  7. 7
    uclanlp/OpenVLHarness

    Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory

    GitHub · Python · 524 stars · 42 forks · 0 stars in 24 hours · Trending score 1.27

  8. 8
    honestDS/MonoLight

    MonoLight is a General Autonomous Agent runtime with IM interaction as its primary interaction modality, focusing on safe execution and human-machine collaboration.

    GitHub · Python · 24 stars · 1 forks · +2 stars in 24 hours · Trending score 0.88

  9. 9
    cosolar/miniwho

    极简简历:把履历写清楚, 让机会看见你。

    GitHub · Vue · 12 stars · 1 forks · +1 stars in 24 hours · Trending score 0.86

  10. 10
    fim-ai/fim-one

    Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

    GitHub · Python · 1,588 stars · 182 forks · +2 stars in 24 hours · Trending score 0.81

  11. 11
    Antoine-Thomas/UH-Universal-Harness

    uh-harness (UH) — local-first, provider-agnostic agent harness for your desktop: chat, memory graph, telemetry, backups, skills. MIT. Not affiliated with the PyPI package universal-harness.

    GitHub · Python · 22 stars · 2 forks · +2 stars in 24 hours · Trending score 0.60

  12. 12
    js-lee-AI/awesome-llm-agent-papers

    LLM agents: curated papers on planning, memory, tool use, multi-agent systems, evaluation, and safety.

    GitHub · Python · 114 stars · 41 forks · 0 stars in 24 hours · Trending score 0.56

  13. 13
    footprintjs/agentfootprint

    TypeScript AI agent framework with recorded context, tool calls and decisions, plus configurable answer checks.

    GitHub · TypeScript · 22 stars · 4 forks · +1 stars in 24 hours · Trending score 0.55

  14. 14
    framerslab/agentos

    TypeScript AI agent framework: cognitive memory, dynamic personalities, emergent behaviors and self-building designs

    GitHub · TypeScript · 691 stars · 102 forks · 0 stars in 24 hours · Trending score 0.42

  15. 15
    SamurAIGPT/muapi-mcp-server

    Mcp server code to setup muapi to work with clients like Claude, Cursor etc.

    GitHub · Python · 14 stars · 8 forks · 0 stars in 24 hours · Trending score 0.37

  16. 16
    V01dMur10c/awesome-agent-rl-environments

    A curated list of training & evaluation environments for LLM/VLM agents (SWE-Gym, GEM, RAGEN, AgentGym, WebArena, OSWorld, ToolBench…). Updated weekly.

    GitHub · 12 stars · 5 forks · 0 stars in 24 hours · Trending score 0.32

  17. 17
    MerkyorLynn/Lynn

    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 & CLI with Coder390 local models

    GitHub · TypeScript · 71 stars · 5 forks · 0 stars in 24 hours · Trending score 0.27

  18. 18
    MZULALI/toolhost

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

    GitHub · TypeScript · 24 stars · 4 forks · 0 stars in 24 hours · Trending score 0.22

  19. 19
    philfung/awesome-computer-use

    Curated resources about automated GUI computer-use via LLMs. Highly opinionated, focus is on quality vs quantity.

    GitHub · 24 stars · 15 forks · 0 stars in 24 hours · Trending score 0.15

  20. 20
    VirajSawad1021/Zyven

    An agent that compiles open-source libraries into verified MCP tools on demand, and keeps only the ones that pass a locked-down sandbox. Open-weight models only.

    GitHub · Python · 5 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09

  21. 21
    Pro-GenAI/Agent-RT

    ⚡ Fastest and lightweight harness for AI agents

    GitHub · Python · 23 stars · 1 forks · −2 stars in 24 hours · Trending score 0.09

  22. 22
    YahyaHammad/Venastine-Research-Harness

    Security-first agentic harness for LLMs, built for long-horizon research in math, computer science and the domain sciences: tool-using chat plus a ten-pass pipeline that fact-checks and scores its own claims.

    GitHub · Python · 7 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09

  23. 23
    MSKazemi/aobench

    Role-aware, permission-enforced benchmark for LLM agents that operate HPC systems — SLURM, telemetry, RBAC, docs, facility. A policy violation hard-fails the task. 88 tasks (10 categories x 5 roles), 29 reproducible environments with 6 rebuilt from real Marconi100 ExaData, scored on 7 weighted dimensions.

    GitHub · Python · 9 stars · 14 forks · −2 stars in 24 hours · Trending score 0.08

  24. 24
    Ling-ye/AgentStrata

    A customizable agent runtime system for external applications, with LangGraph-based agents, application integrations, Harness and Eval.

    GitHub · Python · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08