#tool-calling

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

Mindlas catches your coding agent drifting before the bad code lands. Real-time tracking and correction for context rot, unverified done claims, patch sprawl, and tool loops in your Claude Code session.

Agent tools from many descriptions in a single integration. Authorize operations, not just tool calls, and approve them when a human is required. The agent gets its own identity and never holds your credentials.

OpenHuskyAgent

Reliability for LLM agents through enforcement, not model size — Agent-Contract-Kernel + a fail-closed orchestration engine. Model-agnostic. 🇦🇪 Built in the UAE.

Desktop AI chat app unifying local Ollama models with OpenAI and Claude — includes an agentic mode where the model can read/write files and run shell commands, with every action requiring your approval.

Add an AI assistant to any web application in minutes using an embeddable chat widget and MCP-powered backend tools.

Agent-safe action and workflow runner for TypeScript backends.

An AI Agent workflow using OpenAI Agents SDK, Ollama LLMs, and custom tools to automate tasks like weather retrieval and email communication.

OpenAI-compatible HTTP API for Needle 2, Cactus Compute's 45M-parameter tool-calling model. Drop-in for any OpenAI client.

Talunor is a local-first terminal AI agent written in Go, with persistent, auditable SQLite memory, guarded tool use, and a complete step-by-step course explaining how it is built.

Capability Host Protocol — make agent and tool execution visible, replayable, and ready for governance.

Run local coding agents with full tool access and browser-based monitoring using an uncensored Ollama model on your hardware.

Swift agent runtime for Apple platforms. Keeps tools, skills and history inside the 4,096-token on-device window, so connecting an MCP server doesn't break the turn. FoundationModels / MLX / OpenAI / Anthropic / Gemini.

Production-ready AI Coding Agent built with LangGraph, Groq, Code RAG, Tool Calling, FAISS, Tree-sitter, and Docker. Supports code understanding, retrieval, editing, terminal execution, and debugging.

Chatbot con IA (Groq Llama 3.3 + tool-calling) que agenda y gestiona citas de una clinica dental en SQLite. Express, seguridad hardening, 47+ tests, CI/CD y deploy en Railway.

Local CLI to turn failed AI agent traces (wrong tool, bad args, over-refusals) from LangSmith/Langfuse into clean SFT/DPO fine-tuning data

A MCP-based agent architecture that integrates a large language model with external tool execution to demonstrate structured, controlled interaction between language reasoning and system-level automation.

AI/LLM automation reference: RAG, tool calling, human review, evals, observability, safety gates, and local deterministic samples.

面向 HR 的简历初筛 Agent：规则引擎打分（硬性条件一票否决）+ 大模型语义复核，评分全程可解释，输出 CSV/JSON 筛选报告与面试问题

基于 DeepSeek Harness 的智能客服工单处理 Agent：自动分类、优先级评估、知识库检索（BM25）与建议答复，结论写回 SQLite 并可全程审计

A Rust-first CLI agent built for real work: durable sessions, multi-provider runs, governed tools, modular workflows, and a human checkpoint before software can change your system.

OpenAI and Claude API purity checker with no-store local reports

AI scheduling agent built with Google ADK and Gemini, featuring tool calling, conflict detection, task management, and free-slot discovery.

Run local coding-agent tool loops against OpenAI-compatible Chat Completions providers.

Lightweight multi-provider AI SDK for ASP.NET Core — OpenAI, Anthropic, Gemini, Ollama, Azure. Streaming, structured output, tool calling. Zero Semantic Kernel dependency.

An AI data analysis assistant based on DeepSeek Streamlit (with a data snapshot feature to save tokens) that supports natural language-driven data exploration and visualization. (Supports Excel and MySQL)一个基于DeepSeek+Streamlit的AI数据分析助手（具有数据快照功能，可节省token），支持自然语言驱动的数据探索和可视化。（支持excel和MySQL）

Runtime governance for AI agent tool calls: gates shell, filesystem, network, and credential access before execution.

A professional-grade AI Agent implementation using Model Context Protocol (MCP) for dynamic tool discovery and execution. Built with Python and GapGPT (GPT-gpt-4o).

An Elixir/OTP AI agent runtime: define agents, connect any OpenAI-compatible model, and run a tool-calling loop. CLI, HTTP API, web dashboard, Telegram, WhatsApp.

Typed Rust client for OpenAI-compatible chat completions through Cloudflare

Zendesk MCP for Cursor, VS Code, Antigravity, Bob IDE & Claude — 14 ticket tools. npx @markusvankempen/zendesk-mcp-server · pip install zendesk-mcp-server-py · IBM Code Engine SSE

Autonomous multi-agent engineering-ops copilot — LangGraph agents that investigate, fix, and verify bugs using MCP tools, memory, and a bounded retry/human-approval loop. 100% local via Ollama.