#Tool-calling

Showing 48 of 48 repositories tagged #tool-calling, ranked by stars

Arthur-Ficial
Arthur-Ficial
apfel

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

Score
100
★ 6.1k ⑂ 232 +164/day
Swift
1186258278
1186258278
OpenClawChineseTranslation

🦞 OpenClaw (Clawdbot/Moltbot) 汉化版 - 开源个人 AI 助手中文版 | Claude/ChatGPT LLM 接入 | WhatsApp/Telegram/Discord 多平台 | 每小时自动同步 | CLI + Dashboard 全中文 | 全流程搭建教程,以及排错指南!

Score
100
★ 3.8k ⑂ 482 +6/day
JavaScript
raullenchai
raullenchai
Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

Score
0
★ 3.2k ⑂ 377 +4/day
Python
qingchencloud
qingchencloud
clawpanel

🦞 OpenClaw & Hermes Agent 多引擎 AI 管理面板 — 内置 AI 助手(工具调用 + 图片识别 + 多模态),一键安装 | Tauri v2 跨平台桌面应用 | 11 种语言

Score
100
★ 2.9k ⑂ 355 +2/day
JavaScript
TanStack
TanStack
ai

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.

Score
100
★ 2.9k ⑂ 268 +1/day
TypeScript
antoinezambelli
antoinezambelli
forge

A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows

Score
95
★ 2.2k ⑂ 163 +4/day
Python
alfredfrancis
alfredfrancis
ai-chatbot-framework

A python chatbot framework with Natural Language Understanding and Artificial Intelligence.

Score
33
★ 2.2k ⑂ 749 +2/day
TypeScript
RunanywhereAI
RunanywhereAI
RCLI

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

Score
86
★ 1.5k ⑂ 83 +1/day
C++
wanxingai
wanxingai
LightAgent

LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaboration, and workflows.

Score
91
★ 1.2k ⑂ 156 +2/day
Python
zhu1090093659
zhu1090093659
deepseek-pp

DeepSeek Web browser extension: AI agent workspace with MCP tools, memory, Skills, automation, web search, and conversation export.

Score
100
★ 1.2k ⑂ 157 +18/day
TypeScript
rudrankriyam
rudrankriyam
Foundation-Models-Framework-Lab

A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.

Score
0
★ 1.1k ⑂ 68
Swift
massgen
massgen
MassGen

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

Score
89
★ 1.1k ⑂ 165
Python
LiuMengxuan04
LiuMengxuan04
MiniCode

A lightweight terminal coding assistant with Claude Code-like workflow, tool loop, and TUI architecture, built for learning and experimentation. Multi-language support: TypeScript , Python and Rust implementations available now.

Score
78
★ 974 ⑂ 105 +13/day
TypeScript
AnalyseDeCircuit
AnalyseDeCircuit
oxideterm

AI-native workspace for local shells and remote machines.Zero Electron, zero OpenSSL, zero telemetry, and no app subscription.

Score
67
★ 925 ⑂ 65 +31/day
Rust
Free-The-Ai
Free-The-Ai
free-ai

FreeTheAi (Free The AI): free OpenAI-compatible AI API with 50+ models, Discord key signup, streaming, tools, images, Messages, and Responses. No credit card.

Score
67
★ 776 ⑂ 112
TypeScript
liyupi
liyupi
ai-code-helper

2025 年 AI 编程助手实战项目(作者:程序员鱼皮),基于 Spring Boot 3.5 + Java 21 + LangChain4j + AI 构建智能编程学习与求职辅导机器人,覆盖 AI 大模型接入、LangChain4j 核心特性、流式对话、Prompt 工程、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、Web 爬虫、安全防护、Vue.js 前端开发、SSE 服务端推送等企业级 AI 应用开发技术。帮助开发者掌握 AI 时代必备技能,熟悉 LangChain 框架,提升编程学习效率和求职竞争力,成为企业需要的 AI 全栈开发人才。

Score
0
★ 716 ⑂ 237 +5/day
Vue
jbexta
jbexta
AgentPilot

A versatile workflow automation platform to create, organize, and execute AI workflows, from a single LLM to complex AI-driven workflows.

Score
0
★ 559 ⑂ 80 +1/day
Python
clawdotnet
clawdotnet
openclaw.net

Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)

Score
56
★ 434 ⑂ 82 +2/day
C#
w8123
w8123
EnterpriseAgentFramework

面向 OA、ERP、CRM、工单等企业系统快速构建智能体,让 AI 在权限、审计与治理约束下安全调用真实业务能力。Build agents quickly for enterprise systems such as OA, ERP, CRM, and ticketing, enabling AI to safely call real business capabilities under permissions, audit, and governance controls.

Score
67
★ 398 ⑂ 26 +2/day
Java
lhh737
lhh737
LangChain-ReAct-Agent

基于 LangChain/LangGraph 的 ReAct Agent ,结合 RAG、工具调用与 Streamlit 界面,面向智能客服与报告生成场景。

Score
82
★ 264 ⑂ 58 +1/day
Python
ddalcu
ddalcu
mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

Score
77
★ 258 ⑂ 18 +23/day
Zig
QVerisAI
QVerisAI
qveris-agent-toolkit

Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs for agents to discover, inspect, call, and audit real-world tools.

Score
44
★ 241 ⑂ 22 +2/day
JavaScript
however-yir
however-yir
knowledgeops-agent

Enterprise-ready Spring AI platform for RAG, tool calling, async ingestion, JWT/RBAC security, and observability.

Score
68
★ 215 ⑂ 16 +1/day
Java
Tolga1452
Tolga1452
ai-prompts

A collection of original system prompts and tool data used for AI chatbots. Explore how companies such as ChatGPT prompt their AIs!

Score
73
★ 204 ⑂ 31
TypeScript
GautamVhavle
GautamVhavle
CatGPT-Gateway

Turn your ChatGPT or Claude account into a fully working OpenAI-compatible API. No API keys needed. Supports tool calling, vision, file attachments, and image generation.

Score
64
★ 183 ⑂ 37 +27/day
Python
ratel-ai
ratel-ai
ratel

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 retrieval. No vector DB. No embeddings.

Score
59
★ 181 ⑂ 9 +9/day
TypeScript
Sandermage
Sandermage
sndr_core_engine

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.

Score
55
★ 119 ⑂ 6
Python
IBM
IBM
wxflows

Examples and tutorials for building AI applications with watsonx.ai Flows Engine

Score
32
★ 117 ⑂ 44
mondaycom
mondaycom
agent-tool-protocol

Agent Tool Protocol

Score
50
★ 99 ⑂ 11
TypeScript
TheUncharted
TheUncharted
zapcode

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

Score
33
★ 87 ⑂ 4
Rust
Bobsilvio
Bobsilvio
ha-claude

Home Assistant add-on: Claude Code, OpenAI/GPT, Gemini

Score
45
★ 80 ⑂ 7
Python
csy-csy123
csy-csy123
pr-review-agent-council

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。

Score
41
★ 80 ⑂ 5 +1/day
Python
sandydasari
sandydasari
openacme

An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.

Score
22
★ 80 ⑂ 3
TypeScript
deep-copilot
deep-copilot
DeepCopilot

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

Score
33
★ 77 ⑂ 7 +1/day
JavaScript
fastxyz
fastxyz
skill-optimizer

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

Score
11
★ 70 ⑂ 11 +1/day
TypeScript
seaworld008
seaworld008
Commonly-used-high-value-skills

High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows. 高价值的 AI 技能库,涵盖 Codex、Claude Code、OpenClaw、代理、提示和自动化工作流程。

Score
0
★ 60 ⑂ 9 +1/day
Python
ArmorerLabs
ArmorerLabs
Armorer

Local control plane for running AI agents with sandboxes, approvals, guardrails, credentials, and runtime health.

Score
100
★ 58 ⑂ 3
TypeScript
however-yir
however-yir
tianji-ai-agent

Spring AI agent engineering project with Java, MCP, RAG, tool calling, multimodal workflows, and UI prototypes.

Score
36
★ 44 ⑂ 2
Java
Geekgineer
Geekgineer
needle-rs

258 KB WASM runtime for Needle a 26M-parameter tool-calling transformer. Runs in browser, Cloudflare Workers, and Node.js. No backend required.

Score
0
★ 42 ⑂ 4 +1/day
Rust
ArmorerLabs
ArmorerLabs
Armorer-Guard

Fast local Rust scanner for AI-agent prompt injection, credential leaks, exfiltration, and risky tool calls

Score
0
★ 40 ⑂ 10
Rust
achaljhawar
achaljhawar
1rok

Multi-LLM trading harness.

Score
0
★ 39 ⑂ 9
TypeScript
Harsh-2909
Harsh-2909
hermes-go

An AI Agent framework in Go for building Agents with RAG, Knowledge, Memory, Tools

Score
0
★ 30 ⑂ 3 +2/day
Go
dakotamurphyucf
dakotamurphyucf
ochat

Text-first toolkit for building reproducible, composable LLM workflows as plain files in OCaml.

Score
18
★ 29 ⑂ 3
OCaml
iovdin
iovdin
tune

llm chat in text file

Score
27
★ 28 ⑂ 5
JavaScript
Tom-Ryder
Tom-Ryder
AgentRunKit

Swift 6 agent SDK: type-safe tools, streaming, cloud + on-device inference via MLX on Apple Silicon

Score
23
★ 26 ⑂ 4 +1/day
Swift
kongusen
kongusen
loom-agent

Python agent framework with AgentHarness: planner → generator ⇄ evaluator loops for long-running tasks—plus sessions, tool/safety policies, and Claude, GPT, or Gemini.

Score
14
★ 24 ⑂ 1
Python
lydakis
lydakis
alloy

Python for logic. English for intelligence.

Score
9
★ 18 ⑂ 0
Python
ankitkumarbarik
ankitkumarbarik
GenAI

GenAI 🧠 - 𝘸𝘰𝘳𝘬 𝘪𝘯 𝘱𝘳𝘰𝘨𝘳𝘦𝘴𝘴...

Score
5
★ 17 ⑂ 3
JavaScript
Related Topics
#llm#mcp#ai#openai#rag#ai-agent#ai-agents#python#function-calling#agent#cli#anthropic

© 2026 GitRepoTrend · GitHub repositories by topic · Updated weekly