Javascript agents

Zero-dependency multi-agent orchestrator with a file-based mail model for AI coding agents (Claude Code, Codex, Gemini, Hermes). Agents talk by reading and writing files; the orchestrator routes the mail.

Local MCP server for structured multi-agent workflow state, checkpoints, and handoffs

React components + hooks for rendering kaboo multi-agent activity in a CopilotKit app, with batteries-included CopilotKit integrations.

Lightweight multi-agent coordinator for Hermes-agent: board state, role nodes (Conductor / Builder / Reviewer / Scout), A2A contract-driven task routing, and multiplexer-friendly terminal event streams.

MCP Server for Spec-Driven Development (SDD) — contract validation, task board, and file reservation for multi-agent AI systems

An open-source multi-agent AI team built on Agency Swarm (linux arm64 TUI binary)

Spec-driven development toolkit for AI coding agents: end-to-end workflows, multi-agent coding and review, living specs, and engineering guardrails

Auditable multi-agent coordination for OpenCode — parallel agent fleets with P2P messaging, witnessed receipts, and quorum ratification. Who saw this, who approved it, prove it.

An open-source multi-agent AI team built on Agency Swarm (win32 x64 TUI binary)

An open-source multi-agent AI team built on Agency Swarm (linux x64 TUI binary)

An open-source multi-agent AI team built on Agency Swarm (darwin arm64 TUI binary)

Umbrella package for the Agent Framework (TypeScript): one install for the core, the OpenAI / Anthropic / Foundry providers, MCP, A2A and hosting, each re-exported under a subpath.

A pi agent framework that orchestrates coordinated sub-agent teams directly from the .pi/ithacus folder.

NexusGenesis Agent Framework — self-sovereign keys (PQC security) + coordination (tasks, reputation, governance). Private keys never leave the agent/browser.

AI Coding Agent Framework — interactive bootstrap CLI

TealTiger governance middleware for the Mastra TypeScript agent framework

MCP-native AI Agent Framework — give Claude / OpenCode / Cursor a project-agnostic engineering brain via MCP

A from-scratch TypeScript agent SDK - agent loop, tools, guardrails, sessions, handoffs, structured output, streaming, and tracing. No agent framework dependency.

An open-source AI Agent framework in TypeScript with tools, memory, and guardrails support.

XRLF Protocol — Universal OpenAI-compatible proxy that gives any LLM foveated ring memory, active recall, and cognitive steering. Point LM Studio, Ollama, or any OpenAI SDK at http://127.0.0.1:8300/v1 and it just works.

Turn reviewed MCP failures into deterministic recovery evidence and executable regression tests.

Official CLI for the Arbiter Control Plane for AI Agents — Authority Connect, manifest, and MCP gateway

LangGraph runtime adapter for nestjs-agentic enabling stateful graph-based agent orchestration with NestJS governance.

LangChain Agents (LangGraph) provider for @launchdarkly/ai-server

Programmatic JS/TS SDK for doc2mcp — convert any docs URL into a hosted MCP server from code, CI, LangChain, and LangGraph.

Proof-carrying memory for any agent framework — gate memory before generation, get an Answer Receipt. Adapters for LangGraph, the OpenAI Agents SDK, and anything else.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.

AI-friendly TypeScript rules engine for serializable JSON business rules and deterministic workflow decisions.

<p align="center"> <img src="https://raw.githubusercontent.com/cacheplane/dawnai/main/docs/brand/dawn-logo-horizontal-black-on-white.png" alt="Dawn" width="180" /> </p>

CLI and MCP server for live Dizko event discovery.

OIDC trusted publishing setup package for @memberjunction/ai-agent-harness

Lynx trace analysis AI agent

AI agent orchestration toolkit. Seven subcommands:

Headless AI Agent Runtime — multi-host, MCP-compatible

Metacognitive AI agent oversight — pure CLI with JSON I/O

An account per AI agent, with keys the model never sees.

Approval UX + Cloudflare-native durable execution for AI agent workflows

AI agent worktree and dev artifact garbage collector

BehaviorOS Core Engine — 7 behavioral engines for AI agent governance

AI Agent 开发流程治理 CLI 工具

BehaviorOS SDK — TypeScript SDK for integrating with AI agent orchestrators

Secure Agent Control Plane & Passport Vault — identity-aware reverse proxy for AI agent credentials.

AEO Next.js Middleware — AI agent content optimization

skrun — manage AI agent skills across projects

BehaviorOS DNA Catalog — 12 behavioral patterns for AI agent teams

花漾TK 命令行工具，供 AI Agent 调用花漾TK平台 API

AI Agent 环境诊断工具 —— 一条命令诊断你的 AI Agent 环境哪里有问题

MCP server exposing all 14 presentation-md tools (render/export/audit/judge/scaffold/share/deploy/import/preview) to any MCP-compatible AI agent.

Colorful CLI to discover and call x402-payable AI agent services on minia2a.uk. Zero deps.

MCP server and REST API for persistent, typed AI-agent memory.

Standalone Real Memory AI Agent CLI for project chat, coding workflows, provider configuration, and safe Git operations.

AI Agent Toolkit - CLI unificada para herramientas de desarrollo impulsadas por IA

TypeScript-native workflow engine for AI agent orchestration — code as config, no DSL

Wunderkind — specialist AI agent addon for OpenCode with 6 retained specialist agents for any software product team

Signed, searchable, provider-neutral AI agent discovery with live schemas and A2A, MCP, Arazzo, and WebMCP interfaces.

Self-hostable API, viewer, and CLI for sharing AI agent conversation threads

A streaming chat client SDK for AI Agent conversations

Parasitic AI Agent Token simulator — writes mock usage into ~/.claude and ~/.codex with real JSONL schemas.

TypeScript SDK for the Teardrop AI agent API

High-performance fuzzy file finder for Node.js - perfect for LLM agent tools

High-performance fuzzy file finder for Bun - perfect for LLM agent tools

Minimal tool-loop harness for LLM agents. Keep your provider SDK, keep your messages, add a correct tool loop.

睿思多智能体管理系统 CLI 工具

AI-Zen Agents SDK — shared business logic for CLI and Desktop

Code organized into context-bounded cells for LLMs coding alongside humans.

Accessible Agent Runtime console for Markdown/wiki Knowledge Source endpoints.

LangChain and LangGraph integration primitives for streaming OpenUI generative interfaces

MCP server for pulr.ai — secure FILE exchange infrastructure for AI agents: upload, share, fetch, and revoke durable, verified, expiring file artifacts (reports, CSVs, images, PDFs) with provenance, scanning, and audit. Backend file handoff — not a UI str

Unified observability for AI agents and infrastructure. One SDK.

LiveKit voice integration for Mastra agents — realtime voice with semantic turn detection and barge-in

CryptoAPIs x402 buyer SDK — a fetch wrapper that auto-pays HTTP 402 responses (authorize → sign locally → retry). Non-custodial: you provide the signer; keys never enter the SDK.

Native LangChain tools for Agentlink read-only queries.

DBOS durable execution integration for the Vercel AI SDK

OpenAI provider plugin for Shiro.

LLM agents for GraphAI.

Janux embedded agent runtime: zero-config model resolution, provider routing and the ui/api tool loop.

Show OpenAI Codex, GitHub Copilot, Z.ai GLM Coding Plan (global and China), and DeepSeek balance usage in the pi coding agent.

Semantic diff review for coding agents: an LLM turns a git diff into a narrative HTML report, a human comments on it, and the feedback comes back as plaintext.

Core SDK package for Shiro.

AirRoute — free AI gateway. One endpoint, many free providers, auto-fallback, adaptive auto routing, token compression, and a full admin console. Works with Claude Code, OpenCode, Cline, Copilot & any OpenAI/Anthropic-compatible agent.

Statsig helps you move faster with feature gates (feature flags), and/or dynamic configs. It also allows you to run A/B/n tests to validate your new features and understand their impact on your KPIs. If you're new to Statsig, check out our product and cre

Stopgap opencode plugin that smooths the OpenAI/Codex GPT-5.6 rough edges (Luna 404s, missing session titles, reasoning-summary markers) until native support lands

Statsig helps you move faster with feature gates (feature flags), and/or dynamic configs. It also allows you to run A/B/n tests to validate your new features and understand their impact on your KPIs. If you're new to Statsig, check out our product and cre

CoDev — AI Coding Agent Hub. Install, configure, and manage multiple AI coding agents.

AI-native CLI for geotechnical engineering

SamAI SDK is a provider-agnostic TypeScript AI SDK for building AI agents, chatbots, tool calling, RAG, MCP, streaming, voice agents, and multi-provider LLM applications using OpenAI, Claude, Gemini, Groq, Mistral, Ollama, Azure OpenAI, and AWS Bedrock.

Telnyx Agent Toolkit for TypeScript — tools for OpenAI, Vercel AI SDK, and LangChain.js

Official Olamto Autonomous Agent SDK for Cloudflare Workers AI, Robinhood EVM Chain (4663), and Solana MCP Portals

Secure AgentKit wallet for autonomous AI agents on Base — TEE-backed signing, programmatic guardrails, and zero secrets on disk via 1Claw

Storefront runtime SDK for DoSwiftly Commerce — layered transport, middleware pipeline, React providers, Zustand stores, cache strategies. 0 runtime dependencies in core.

LexVibe MCP server — one-step legal compliance for vibe-coded apps: privacy policy, terms of service, cookie consent banner and EU AI Act check from Claude Code, Cursor, Codex, Gemini CLI or any MCP client.

SDK for programmatic control of Letta agents

AI SDK middleware for tool call parsing

Helix CLI — helix init, helix dev, helix auth

TypeScript SDK for Railway.

Headless React primitives for AI chat — state management, streaming adapters for OpenAI, Vercel AI SDK, and AG-UI, message format converters, and thread management for OpenUI generative UI apps

Selective Codex skills, lean hooks, indexed memory, and optional multi-agent orchestration

Project-aware, evidence-driven operating system, multi-agent CLI, and secure MCP desktop bridge for coding agents.

Local-first multi-agent memory MCP. Shared SQLite + FTS5, secret-blocking, lite transport (no SDK by default), namespaces, batch + handoff tools.

Abstractflow — zero-config JavaScript AI Agent SDK with tools, guardrails, multi-provider models, and multi-agent handoffs. Install, drop your key in .env, run.