#Tool-use

Showing 32 of 32 repositories tagged #tool-use, ranked by stars

esengine
esengine
DeepSeek-Reasonix

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability β€” leave it running.

Score
0
β˜… 26.6k β‘‚ 1.7k β€”
Go
NVIDIA-NeMo
NVIDIA-NeMo
DataDesigner

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

Score
100
β˜… 2.1k β‘‚ 193 +9/day
Python
mims-harvard
mims-harvard
ToolUniverse

Democratizing AI scientists with ToolUniverse

Score
100
β˜… 1.6k β‘‚ 235 +28/day
Python
Agent-RL
Agent-RL
ReCall

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

Score
65
β˜… 1.4k β‘‚ 87 +5/day
Python
fim-ai
fim-ai
fim-one

Open-source agent platform for Global Γ— China enterprises β€” wire every system through one agent core. Self-hosted, any LLM.

Score
0
β˜… 1.3k β‘‚ 147 +9/day
Python
moltlaunch
moltlaunch
cashclaw

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

Score
95
β˜… 1.1k β‘‚ 215 β€”
TypeScript
sigoden
sigoden
llm-functions

Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.

Score
50
β˜… 759 β‘‚ 132 β€”
Shell
zhudotexe
zhudotexe
kani

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

Score
85
β˜… 604 β‘‚ 30 β€”
Python
framerslab
framerslab
agentos

TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

Score
90
β˜… 591 β‘‚ 88 +2/day
TypeScript
henrydaum
henrydaum
second-brain

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

Score
0
β˜… 576 β‘‚ 67 β€”
Python
AgentTeam-TaichuAI
AgentTeam-TaichuAI
ScienceClaw

ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stronger security, better transparency, and a more user-friendly experience.

Score
0
β˜… 551 β‘‚ 62 +4/day
Python
bigcode-project
bigcode-project
bigcodebench

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

Score
75
β˜… 513 β‘‚ 74 +1/day
Python
CraftOS-dev
CraftOS-dev
CraftBot

One agent. Every kind of work.

Score
80
β˜… 367 β‘‚ 39 +1/day
Python
linghungegeg
linghungegeg
Linghun

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

Score
100
β˜… 268 β‘‚ 25 +19/day
TypeScript
DemonDamon
DemonDamon
AgenticX

AgenticX is a unified, production-ready multi-agent platform β€” 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).

Score
70
β˜… 182 β‘‚ 33 +2/day
Python
seuros
seuros
action_mcp

Rails Engine with MCP compliant Spec.

Score
50
β˜… 116 β‘‚ 19 β€”
Ruby
wulawulu
wulawulu
learn-claude-code-rs

Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and typed tool routing.

Score
0
β˜… 114 β‘‚ 20 +6/day
Rust
kangarooking
kangarooking
system-prompt-skills

从 165 δΈͺι‘ΆηΊ§ AI δΊ§ε“η³»η»Ÿζη€Ίθ―δΈ­θ’Έι¦ε‡Ίηš„ 15 δΈͺε―ζ‰§θ‘Œ Agent skill

Score
60
β˜… 108 β‘‚ 29 +8/day
skissue
skissue
llm-tool-collection

Curated collection of tools for agentic LLMs in Emacs

Score
30
β˜… 93 β‘‚ 10 β€”
Emacs Lisp
oneal2000
oneal2000
SR-Agents

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

Score
55
β˜… 89 β‘‚ 11 +1/day
Python
NJUxlj
NJUxlj
Travel-Agent-based-on-Qwen2-RLHF

A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using the response. A RAG system is build upon the tuned qwen2, using Prompt-Template + Tool-Use + Chroma embedding database + LangChain

Score
45
β˜… 80 β‘‚ 6 β€”
Python
alloy-ex
alloy-ex
alloy

Model-agnostic agent harness for Elixir

Score
40
β˜… 77 β‘‚ 6 β€”
Elixir
aaronnat23
aaronnat23
disp8ch

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

Score
35
β˜… 75 β‘‚ 1 β€”
TypeScript
sazonovanton
sazonovanton
SirChatalot

SirChatalot is a Telegram bot leveraging ChatGPT, Claude or YandexGPT. It uses Whisper for speech-to-text and DALL-E, Stability AI or YandexART for image creation. It can use vision capabilities, tools and semantic search in vector DB.

Score
0
β˜… 73 β‘‚ 13 +1/day
Python
FractalAIResearchLabs
FractalAIResearchLabs
Fathom-DeepResearch

Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval And Synthesis For SLMs

Score
0
β˜… 60 β‘‚ 10 β€”
Python
Camil-H
Camil-H
cli-agent-lint

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.

Score
0
β˜… 57 β‘‚ 4 β€”
Go
xemantic
xemantic
xemantic-ai-tool-schema

AI/LLM tool use (function calling) JSON Schema generator - a Kotlin multiplatform library

Score
100
β˜… 51 β‘‚ 3 β€”
Kotlin
mozex
mozex
anthropic-php

PHP client for the Anthropic API: messages, streaming, tool use, thinking, web search, code execution, batches, and more.

Score
25
β˜… 48 β‘‚ 9 β€”
PHP
alexk-dev
alexk-dev
golemcore-bot

Agent Platform for AI-Native Companies

Score
20
β˜… 41 β‘‚ 4 β€”
Java
josephsenior
josephsenior
Agentic-Design-Patterns

Complete Implementation of 21 Agentic Design Patterns A comprehensive collection of production-ready AI agent patterns, each as a runnable project. Master agentic design through practical examples covering prompt chaining, multi-agent systems, RAG, and more. Perfect for AI developers, researchers, and teams building complex AI workflows

Score
5
β˜… 29 β‘‚ 8 +2/day
Python
Null-Square
Null-Square
Agent-Behavior-Lab

A controlled-experiment lab for studying how tool-using LLM agents behave β€” vary tools, personas, and conversation histories, run repeated trials across models, and measure the effect on safety and tool-call behavior.

Score
15
β˜… 26 β‘‚ 0 +26/day
TypeScript
agenticloops-ai
agenticloops-ai
agentic-apps-internals

AI Agents internals - system prompts, tool architectures, and implementation patterns

Score
10
β˜… 24 β‘‚ 2 β€”
Python
Related Topics
#llm#ai-agents#agentic-ai#ai#mcp#function-calling#rag#ai-agent#agent#multi-agent#agents#claude

Β© 2026 GitRepoTrend Β· GitHub repositories by topic Β· Updated weekly