Javascript agents

Stops LLM agents from silently guessing what they don't know

Static, evidence-backed health checks for AI agent projects

CDS Plugin for LangGraph checkpoint persistence in SAP CAP applications

Evidence-preserving LangGraph Store adapter for Engram.

LangGraph adapter for Context Router - brings structured state to LangGraph workflows

A generic Pi extension that implements LangGraph-like workflows with transitions, joins, dynamic fan-out, and configurable node runners.

LedgeLM evaluation helpers for LangGraph graphs and nodes

Deterministic testing helpers for @harpua/langgraph graphs: scripted chat models, stream collectors, interrupt assertions, and a Nest testing-module harness

Scaffold a runnable NestJS + LangGraph weather agent built on @harpua/langgraph — `pnpm create harpua-app my-agent`

OpenClaw plugin that lets any agent drive LangGraph workflows from inside a conversation thread with proactive event wake-back.

CLI to inspect LangGraph agent trajectories locally - zero infra, localhost only

Codex-style LangGraph agent runtime for internal non-coding workflows.

TUI Agent 脚手架：LangChain + LangGraph + DeepAgents + ACP 协议

Machine-first CLI used by a Node LangGraph agent to execute semantic Wave operations against the Rails API.

FDE agent substrate — A2A contract, ports, LangGraph agent runtime shell

AG-UI lifecycle and concurrency checker for LangGraph agents

Event schema, LangGraph adapter, and approval helpers for Agent Action Inspector

Phone approvals for LangGraph and LangChain agents. Your agent asks, your user taps Approve or Deny.

Zod contracts for the self-hosted CopilotKit and LangGraph thread platform

A LangGraph-inspired Pi agent graph extension with durable execution, bounded state, artifacts, and explicit agent context modes

LangChain and LangGraph integration for the Outsail Context Intelligence Platform

bibbi: A personal AI Agent built with LangGraph, featuring tools, memory, hooks, sub-agents, and MCP servers. Run in the terminal.

LangGraph-based graph orchestration system with composable nodes for AgentOS

Adaptive agentic engineering harness: triage-routed dual-path (FAST/HEAVY) agent with business-logic pre-flight validation, abstract-graph planning, coverage-driven loops and self-applying diffs. Built on LangGraph.

Natural-language pipeline planner for OpenPipeline: an LLM-driven design -> validate -> correct loop over LangGraph that produces a valid PipelineDraft.

Framework adapters that wire TryAgent human-in-the-loop guardrails into LangGraph, the Vercel AI SDK, and the OpenAI Agents SDK.

Agent orchestration mock harness for kiwa — LangGraph-style state machine (StateGraph.addNode + addEdge + compile → invoke / stream) and OpenAI Assistants v2 (Assistant + Thread + Message + Run + run.poll) unified under one API. Ships stateful conversatio

Receipt every tool call in a LangChain or LangGraph run with one callback handler - no changes to your tools. Signed, verifiable Zanii proofs across the whole chain.

Lifts watsonx Orchestrate Slack limits: every-message wake-up (beyond byo_slack @mention/DM), multi-channel→multi-agent routing, clean gateway_thread replies, streamable-http /mcp for WxO + Cursor/VS Code/Bob/Antigravity/LangGraph. By Markus van Kempen —

Durable LangGraph workflow runtime: registry, Postgres checkpointer, case-file DI seam, base state schema.

Supervised inter-agent messaging relay for Claude Code and OpenCode (and any MCP client). Projects, environments with web consoles, focused conversations with state docs (PROGRESS.md), LangGraph review subagents, multi-provider LLM supervision, single-pan

Human-in-the-loop for LangGraph.js over Telegram — surface interrupt() payloads as approve/reject/edit buttons in a Telegram chat and feed the human's answer back into the graph via Command(resume).

SurrealDB checkpoint saver, store and node cache for LangGraph.js, plus a SurrealDB Agent Memory store

Headless agent-workflow model (Handoff 12 A-1): the JSON schema for a governed AI-agent sub-workflow — exactly three node types (llm/tool/decision) plus decorators (memory/planner/errorBoundary) — a versioned id@semver reference parser, and graph validati

Typed code-mode tool orchestration for LLM agents: tools become TypeScript declarations, generated programs are type-checked (routeable checker backends), repaired via diagnostics, and executed in a QuickJS sandbox.

CLI for toolgovern -- validate policy files, audit local gate traces, and scaffold framework integration boilerplate, with a --json output mode for programmatic/agent use.

Platform-agnostic JSX channel engine for CopilotKit (createChannel, Thread, PlatformAdapter, ActionStore).

Normalize native agent transcripts into a shared trajectory format.

Proactivity primitives for autonomous agents — scheduling, governance, goals, briefing

Local-first Engram Studio CLI.

A versioned, searchable JSON workspace for AI agents: scoped edits, semantic discovery, audit history, time-travel, and delta persistence.

PipelineEngine orchestrator for OpenPipeline — drives a run end to end over the kernel.

Start with a minimal TypeScript LangChain CLI agent, then grow it into an API or chat app.

OpenTelemetry spans and metrics for skein-js runs — works with any OTLP backend.

Optional MCP integration for OpenPipeline: JSON-Schema→Zod converter, MCP client factory, env catalog loader, and mcp:* node resolver.

Sovereign AI Agent Desktop Daemon

Governed AI agent orchestration with repository intelligence, approval gates, specialist workcells, and reviewable evidence.

Open-source AI agent SDK with a built-in runtime. Nothing between you and your agents.

AI Agent JS SDK

Two AI agent seats in one window: one builds, one reviews.

Local AI-agent sessions for Claviz apps.

AI agent skills collection for pi

基于 pi 的安全 SnowLuma QQ AI Agent。

Evidence-based scoped AI agent reputation with W3C Verifiable Credentials 2.0 adapters.

Framework-agnostic conformance suite for AI agent implementations

Consent-based local observer for Phigon AI agent supervision.

Self-contained AI-agent toolkit: deterministic think → draft → forge → shield workflow with zero dependencies at runtime.

AI agent integration plugin for Baseplate — generates AGENTS.md, CLAUDE.md, .mcp.json, and .agents/ configuration files

Model Context Protocol server for refract — query + validate a project's theme from an AI agent.

CLI tool to create Kuikly cross-platform projects. AI Agent friendly.

Local-first GitHub-backed sync for AI agent skills, instructions, and Codex plugins.

AI Agent node (baseado no n8n-nodes-langchain.agent v2.21.0) com tracing para Langfuse

A personal AI agent.

Local HTTPS interception proxy — records desktop AI agent calls (Claude Desktop, Cursor, etc.) to ARKNA

轻灵 Qling - 本地优先的中文 AI Agent CLI 工作台 / Local-first Chinese AI Agent CLI workbench

Provider-independent AI agent workflow system for Claude Code, Codex, Gemini CLI, and Kimi Code

Agent Approve extension for Pi - approve or deny AI agent tool calls from your iPhone and Apple Watch

AI Agent skill with prompting set for development process

Browser multiplayer SDK for games generated by Loova AI Agent

TypeScript SDK for the AfterQuery compute API — isolated sandboxes for AI agent pipelines

Ainnov8 embeddable web component widget for AI agent interactions

AI-agent-friendly web spider: structured output, RAG-ready chunks, graph-traversable links

TypeScript SDK for Atbash — the safety layer that evaluates AI agent actions against operator-defined policies before execution.

Your AI agent, fluent in Australian tax. MCP server with cited answers from 34,500+ Australian Taxation Office documents

Cesium MCP Bridge SDK — AI Agent 操控 Cesium 的统一执行层

Contract-first backend framework — one defineContract() into an HTTP API, MCP tools, AI-agent tools and a typed client. Bun and Node.

TikTok CLI - designed for AI Agent and developers

Local-first archive, search, and recall for AI-agent conversations.

AI Agent for koishi, powered by @cline/sdk

Versioned provider-neutral policy lifecycle, simulation, and AuthZEN adapter for AI agent actions.

ApparelHub MCP server: workflow-level tools that let an AI agent design apparel, build products, and sync them to sales channels through the ApparelHub platform.

DeepSeek AI Chat Model sub-node for n8n AI Agent workflows (V4-native)

Move your AI agent between clients — config, MCP servers, skills, memory, persona. Any direction, dry-run first, lossless where possible.

Ory Argus: the core API for building authentication, authorization, and audit into AI agent harness plugins, extensions, and custom integrations

Neural router for AI agent orchestration - linux-arm64-gnu platform

Track AI agent interactions (MCP tool calls and more) with Keoki analytics.

SOLAI Agent is a local-first AI agent and coder that runs locally on your computer.

AnyCap CLI - AI Agent capability runtime

n8n community node for Manus AI — create, manage and monitor AI agent tasks programmatically.

JS reverse engineering MCP server with agent-first tool design and built-in anti-detection. 为 AI Agent 设计的 JS 逆向 MCP Server，内置反检测。

Vision Hub CLI - query projects and resources, designed for AI Agent and developers

Zero-dependency LLM agent harness: streaming loop, hooks, tools, replay-time compaction, per-conversation locking.

A local-first, editable knowledge graph for humans and LLMs: npx yamlover <root> serves a browser UI over a plain-text directory, with an editor, live queries, pointers, and an LLM-agent API.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

Brain-inspired associative memory layer for an LLM agent. Automatic (implicit) tier: capture -> embed -> recall. Codename Factor-X.

Dependency-free static analyzer that audits LLM agent tool/function definitions (OpenAI, Anthropic, MCP) for excessive agency, code-execution & SSRF sinks, secret access, and data-exfiltration surface — mapped to the OWASP 2025 LLM Top-10. Runs in CI.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.