Transactional reliability layer and proxy for Model Context Protocol (MCP) tool execution

Concurrency-safe usage enforcement primitives for MCP tool execution.

A durable AI agents component for Convex with automatic retries, crash recovery, and tool execution.

Generic LLM provider SDK with local tool execution for OpenAI-compatible APIs

Open-source AI agent governance for TypeScript: policy, exact one-use approvals, controlled tool execution, and verifiable receipts.

MCP (Model Context Protocol) tool-calling for AI Matey - translate MCP tools into the IR tool-execution loop via an injectable client

The core agent loop for AgentLayer. Wraps Vercel AI SDK's `streamText` in a resumable, approval-aware tool-execution loop, and defines the interfaces that platform packages (`agentlayer-filesystem`, `agentlayer-justbash`) implement. Ships isomorphic tools

Strix MCP Proxy — the distribution wedge for governed agent tool execution. Point your MCP client at the proxy instead of the underlying server; every callTool is intercepted, evaluated against policy, and emits a signed Ed25519 receipt. Designed so Mode

Core client library for Agno agents with streaming support and HITL frontend tool execution

Fail-closed semantic policy guard for secure DeepSeek Harness tool execution.

TypeScript SDK for the Hostler API: managed agents, sessions, live event streams, and client-tool execution.

Voice-to-tool-call browser library: wake word detection, speech-to-text, LLM intent interpretation, tool execution, and text-to-speech

Local control plane for Claude Code: inspect context, remove unused tool schemas, gate risky actions, and audit tool execution.

Wrap Anthropic Tool Use (Claude tool_use blocks) with OC Agent scope enforcement and emit a signed agent-action envelope per tool execution.

Type-safe AI agent library for the KASKO platform. Build AI-powered applications with tool execution, streaming responses, and multi-agent orchestration.

Official JavaScript/TypeScript SDK for Cognipeer AI - Build conversational AI applications with client-side tool execution

DSH 一次性只读旁问插件：基于当前上下文回答，独立气泡，不执行工具 · One-shot read-only side-ask plugin: answers from current context in an independent bubble, no tool execution

Self-hosted tool-execution worker for Hostler — claims parked tool calls from your environment's queue and executes them on your host

The stateful agent daemon runtime: run lifecycle, durable event-log port, the tool-execution boundary, agent executor, terminal sessions, and routines.

ai.matey middleware for code-based tool execution via andbox sandbox