Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.
TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.
CLI + Local MCP - A shared structured memory store across Claude Code, Cursor, Windsurf, Antigravity, and every MCP client. Semantically queryable.
AI Agent which can do any kind of Browser Automation Task & Web Scraping, just using a single prompt!
From-scratch voice agents in Python: end-to-end speech pipelines, runnable chapters, and a small shared library. Local models, explicit streaming behavior.
First-class local model support for pi through Ollama — reliable tools, context management, thinking controls, vision, warm-up, and telemetry.
Deterministic observation-integrity contracts for AI-agent tool results. HTTP 200 is not an observation.
Force deterministic tool execution order in n8n AI Agents. No skipping, no hallucinated parameters.
The AI toolbox you deploy inside your customer's data center — one unified MCP entry with five-layer security and full audit trails. Plugin engine turns Feishu / DingTalk / WeCom / intranet APIs into agent tools. One Docker command, 1-core/1GB min, data never leaves your network. Apache 2.0.
Lightweight open-source toolkit for evaluating tool-calling AI agents on safety, correctness, and reliability
Hallucination Killer — MCP server that grounds LLM answers in live repo context and real-time docs
A high-performance, token-efficient AI Agent tool-calling library for .NET. Replaces JSON with TOON for token savings.
QLoRA fine-tuning of Llama 3.2 3B for reliable structured tool-call generation. Investigating whether ~3,000 curated examples can close the reliability gap between small open models and hosted APIs (GPT-4o, Claude) at <5% of the cost. Runs on free Colab. Data quality > quantity.
An advanced AI scheduling assistant powered by Gemini 2.5 Flash and Streamlit. Effortlessly manage your Google Calendar using natural language and a visual dashboard.
Pulse is an autonomous newsroom that discovers, curates, and publishes content entirely on its own. No human writers needed—just configure your editorial policy and let the AI agents do the rest.
Agentic coding CLI for local models (Ollama, vLLM, llama.cpp) and Anthropic, OpenAI, and Amazon Bedrock.
Store and query shared structured memory across Claude Code, Cursor, Windsurf, and any MCP client with a local CLI and MCP server
Local-first Cognitive Execution Platform for Multi-LLM Orchestration, Autonomous Workflows, Persistent Memory & Offline Learning
Experimental low-overhead Rust agent harness for running tool-using agents across local and cloud LLM providers.
one prompt, one shot, done.
To associate your repository with the tool-calling-agent topic, visit your repo's landing page and select "manage topics."