Tool Use agents

SynthCode - Synthesize any LLM into a production-grade AI agent. Battle-tested agentic patterns…

Model-Agnostic Runtime for Controlled Orchestration — a small, readable AI agent harness.

Local-first AI agent for Windows/WSL/Linux. Autonomous tool chaining across 14+ providers, offline via Ollama.

High-level tool-schema optimizer for LLM agent frameworks. Integrates with LangChain, MCP, Vercel AI SDK.

Provider-agnostic LLM agent framework. One LLMProvider interface, two adapters (Anthropic +…

开箱即用的 LLM Agent SDK — 配个 API Key 就能跑

Tool-using planning agent over MCP servers, built on the Vercel AI SDK.

The Control Plane for AI Agents. 26,701 discoverable APIs, 2,906 callable, 49 fully managed. Agent-native…

Atom is a full-system code agent with root-level access, built for isolated servers.

Embeddable TypeScript agent SDK for DeepSeek — built-in tools, skills, memory, and MCP.

PostBridge postal tools for LangChain JS and LangGraph — send physical letters to 5 countries from any…

Anthropic SDK to multi-provider streaming bridge — converts Anthropic message format and tool calls to…

Wrap OpenAI function-calling (Responses API + Chat Completions tool path) with OC Agent scope enforcement and…

Provider-agnostic autonomous agent loop for JavaScript. Built on the [Vercel AI SDK](https://sdk.vercel.ai/)…

Autonomous agent orchestrator: chained LLM calls, tools, memory, streaming.

TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task decomposition, parallel…

One TypeScript SDK for every local coding agent. ACP transport, Vercel AI SDK provider, cost budgets…

The explainable agent framework — build AI agents you can explain, audit, and trust. Built on footprintjs.

A minimal, extensible TypeScript Agent framework

AI Agent framework for generating faui JSON Schema pages via LLM tool calls

Programmatic SDK for building AI agents with Robota — provides InteractiveSession, createQuery(), command…

Headless agent framework for claude-code-kit — LLM query loop, tool execution, multi-provider

TypeScript AI Agent framework - from single agent to multi-agent cluster orchestration

Self-hosted Claude AI agent framework — gateway, memory, tools, Telegram, cron, heartbeat. Full system access…

Framework adapters for AriKernel — protect agents built with LangChain, CrewAI, OpenAI, and more

MoneyGraph cross-border payment SDK — send payouts to 82+ countries via bank, mobile money, SWIFT, SEPA, ACH…

Open-source coding agent inspired by Claude Code. Multi-provider (Anthropic/OpenAI/Ollama), streaming tool…

Jack into any OpenAPI spec and rip a full-featured CLI with AI-agentic workflow automation

Drop-in middleware wrappers for securing AI agents with Ari Kernel

TypeScript SDK for Merka2a - The B2B exchange for AI agents. Search products, negotiate prices, and place…

The API layer for AI agents. Dashboard + 22K APIs + 18 Direct Call providers. MCP native.

Gate LangChain tool execution through ActionGate primitives before execution.

Gate OpenAI function/tool calls through ActionGate primitives before execution.

Declarative action policies for AI agents — approve, deny, or escalate any tool call before execution

Python SDK for agent input scanning, tool-call guardrails, and audit logs

Pick the right tools for an agent task. Boring baseline. Open dataset.

Lightweight evaluation toolkit for AI agents — test tool use, grounding, safety, and efficiency before…

Network egress firewall for AI agents. Declarative allow/deny list of hosts your agent tools may reach…

Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency…

Production-grade guardrails for AI agent function calls. Prevent overspending, unauthorized purchases, unsafe…

Give any AI agent the ability to make real phone calls. Agent-to-agent voice capability — your AI agent…

LLM-neutral Python agent framework with built-in multi-channel messaging and document automation.

Real-time quality guardrails for AI coding agents

A small, focused library for building Claude-powered agents in Python.

The deterministic merge gate for AI-generated agent capability changes. Agent release readiness for…

A lightweight Python SDK for building AI agents with tools, memory, and multi-agent pipelines — powered by…

Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency…

Snapshot tests for AI agents. Record an agent's tool-call trace, diff against a baseline, fail CI on…

Validate LLM-generated tool args before execution. Wraps tool functions with arg validation, raises…

A lightweight, extensible Python framework for building stateful AI agents with tool use, backed by local or…

High-performance CLI tool to find and repair broken Claude conversation sessions

Export your Claude Code conversations to HuggingFace as rich training datasets

Give your AI agent a wallet. Autonomous agents that send ETH, swap tokens, and manage DeFi — across Ethereum…

Provider-agnostic LLM call_tool router with yaml routing, fallback chains, and cost telemetry.

Hermes Agent Harness (HAH) — Hermes substrate adapter for AI King ecosystem (MIT)

Domain-agnostic chat agent with Tool-Use loop

Tool retrieval and ranking algorithms for LLM agents

SAGE Tool Use Benchmark - Tool selection and use evaluation framework

SAGE Tool Use SIAS - Sample-Importance-Aware Selection for tool selection and agent training

Benchmark autonomous AI agents on task completion, tool use, goal adherence, and safety. Works with any agent…

A Python-native Agent framework with first-class Skill support and multi-LLM adapter

Generate realistic multi-agent workflow traces with LLM-enriched content, semantic validation, and PM4Py…

Quick monkey-patching fix for OpenAI's hallucinated multi_tool_use.parallel

Pascal — autonomous AI employee runtime

PostBridge postal tools for CrewAI — send physical letters to 5 countries from any CrewAI agent.

PostBridge postal tools for LangChain and LangGraph — send physical letters to 5 countries from any LangChain…

PostBridge postal tools for LlamaIndex — send physical letters to 5 countries from any LlamaIndex agent.

Anthropic Claude Agent SDK integration for Sardis payments

A command-line productivity tool powered by large language models (Chinese enhanced, with web search and…

Open-core orchestrator logic for the Siglume API Store agent runtime — tool-manual quality scoring + LLM…

Steward — Autonomous Superagent Engine (Sankhya-25 Architecture)

Model-agnostic LLM execution library

Extract & validate JSON from messy LLM output. Designed for Claude / Codex CLI workflows where tool-use is…

Agent run-loop primitive over Tangle sandbox transports — runs an AgentProfile against a brief with criterion…

Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a…

Agentic chart-of-accounts categorisation for bank transactions, powered by Claude. Production patterns…

Agentic loop core library — provider-agnostic, server-independent

Persistent memory + tool-result intelligence for AI agents — TypeScript SDK. One install, all framework…

Agentic AI audits for tool-use, memory, permissions, and prompt injection

Agentic engine core (release candidate) — descriptor registry, 9-phase execution pipeline, prompt assembler…

Experimental OpenAI-compatible tool-use adapter for Stigmem.

A TypeScript agent framework — ReAct / Plan-Solve agent loops, tool management with circuit breaker, session…

TypeScript SDK for Merka2a - The B2B exchange for AI agents. Search products, negotiate prices, and place…

Synthetic Agentic Trajectories Generator + LLM-as-Judge Eval Loop for fine-tuning agentic LLMs

Multi-model coding agent powered by NVIDIA Llama (3B, 70B) with CLI, web search, and tool-use loop

天空织机 Skyloom — 6 weather-themed AI agents: Fog, Rain, Frost, Snow, Dew, Fair

Convert chat conversations and responses between OpenAI, Anthropic and Gemini. Tool calls, images, audio…

Reliability and reproducibility statistics for stochastic agent / tool-use evals.