AI agent tools for function calling
Short answer: Our top pick for function calling: Composio, with the highest AgentPick Score (87/100) among tools tagged "function-calling". Runners-up: langroid (77) and ai (77). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | Composio | Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn inten… | 87/100 | ★ 31k | MIT | 14 Oct 2026 |
| #2 | langroid | Harness LLMs with Multi-Agent Programming | 77/100 | ★ 4.1k | MIT | 14 Oct 2026 |
| #3 | ai | 🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, Reac… | 77/100 | ★ 3.2k | MIT | 14 Oct 2026 |
| #4 | agentdock | Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration. | 70/100 | ★ 1.2k | Apache-2.0 | 14 Oct 2026 |
| #5 | bolna | Conversational voice AI agents | 70/100 | ★ 793 | MIT | 14 Oct 2026 |
| #6 | yomo | 🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra. | 65/100 | ★ 1.9k | See repo | 14 Oct 2026 |
| #7 | forge | A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows | 63/100 | ★ 2.3k | MIT | 14 Oct 2026 |
| #8 | LightAgent | LightAgent: Lightweight Python framework for OpenAI-compatible agents with tools, memory, guardrails, tracing, lifecycle hooks, multi-agent collaborat… | 62/100 | ★ 1.2k | Apache-2.0 | 30 Sept 2026 |
| #9 | dexto | Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included | 62/100 | ★ 652 | See repo | 12 Oct 2026 |
| #10 | corsair | Connect your users to their apps | 57/100 | ★ 14k | See repo | 14 Oct 2026 |
| #11 | MakerAi | The AI Operating System for Delphi. 100% native framework with RAG 2.0, autonomous agents, MCP protocol, and universal LLM connector. Supports OpenAI,… | 57/100 | ★ 214 | MIT | 14 Oct 2026 |
| #12 | core | AI agent microservice | 55/100 | ★ 3.1k | GPL-3.0 | 29 Jul 2026 |
| #13 | klavis | Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale | 42/100 | ★ 5.8k | Apache-2.0 | 1 Jun 2026 |
| #14 | PokeClaw | PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket. | 41/100 | ★ 1.1k | Apache-2.0 | 2 Jun 2026 |
| #15 | fim-one | Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM. | 40/100 | ★ 1.6k | See repo | 10 Oct 2026 |
| #16 | aci | ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a… | 39/100 | ★ 4.9k | Apache-2.0 | 28 May 2026 |
| #17 | superglue | superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long tail and enterprise systems. | 37/100 | ★ 2.1k | See repo | 19 Aug 2026 |
| #18 | ai-agents-from-scratch | Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns. | 36/100 | ★ 4.8k | MIT | 24 Jul 2026 |
| #19 | aichat | All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more. | 35/100 | ★ 10k | Apache-2.0 | 23 Feb 2026 |
| #20 | functionary | Chat language model that can use tools and interpret the results | 30/100 | ★ 1.6k | MIT | 30 Jun 2026 |
| #21 | llama-cpp-agent | The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execu… | 17/100 | ★ 659 | See repo | 9 Mar 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.