npm agents

One-line MCP bridge to the Kenwea agent marketplace. Connect any MCP-speaking agent (Claude Desktop, LangChain, CrewAI, custom) to mcp.kenwea.com — stdio<->HTTP proxy plus init and doctor helpers.

MCP server that lets Claude, Cursor, LangChain and CrewAI call 35 live x402 pay-per-call tools on Base (USDC) with no API key. Agents auto-pay per call via the x402 v2 protocol using their own funded wallet: cited SEC EDGAR company data, RDAP domain-trust

CLI for the Team API as Code toolchain: validate, render, scaffold, generate, serve-api, serve-mcp, chat

URL → PNG/JPEG/PDF capture API + MCP server for AI agents (Claude, Cursor, Copilot)

The Context Company CLI — zero-friction AI agent observability setup

CLI for Studio — declarative YAML runtime for AI agents with structured output validation

Terminal rug/honeypot check for any Base token — `npx @true402.dev/rugcheck 0x…` — pay-per-call over x402 (USDC, no account, no API key).

Compress a completed agent's trace into a compact, framework-agnostic briefing that the next agent can load in one call. Solves the cross-framework agent-to-agent handoff problem. Paid via x402 ($0.10/pack) on Base USDC.

MCP server for StackMap — the curated map of the open-source AI stack. Search 200+ human-reviewed repos, typed relationships (complements / alternative / built_with), and the written why behind every connection.

UserVane frontend capture for CopilotKit (deterministic turn-resolution feedback)

MCP server for StackMap — the curated map of the open-source AI stack. Search 200+ human-reviewed repos, typed relationships (complements / alternative / built_with), and the written why behind every connection.

Trust-gated buyer client for the x402 machine economy — spend policy, Aegis trust gate, receipts ledger, MCP server, LangChain.js tools.

Send one controlled Claw Messenger message from n8n and prove the matching reply in your consumer

Static Kubernetes audit for agent candidate workloads that may bypass MCP/runtime enforcement hops

Register your AI agents with Span's intelligent task orchestrator

Prismor for Mastra — policy-controlled tool calls via a wrapped execute function and the Prismor eval-server

Somoy (Bengali for 'time') — a transparent, hand-rolled AI Agent SDK for TypeScript. Provider-agnostic, zod-typed, runtime-agnostic (Bun + Node 18+).

Server-first TypeScript SDK for GlobiGuard control-plane and trusted decision-engine connectivity.

MCP server for Spctre policy governance

Official JS/TS SDK for MCPGRAM — one client for native connectors and external MCP servers.

AI governance SDK — intercept, audit, and control AI agent tool calls. Add human-in-the-loop approval, kill switches, and a full audit trail to any AI agent.

MCP server for Beacon — the search engine for AI agents. Find open-source AI agents by capability, ranked by real GitHub traction, right inside Claude/Cursor/Cline.

The official command-line interface for Creduent: the open standard and security protocol for cryptographic AI agent identity, authentication, and trust verification using Ed25519 and DNS.

Official TypeScript SDK for the DocImprint document intelligence API

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

Static, evidence-backed health checks for AI agent projects

CDS Plugin for enabling persistence in LangGraph/LangChain/DeepAgents - Checkpoint & Memory

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

Human-in-the-loop for LangGraph and LangChain: a blocking ask_human tool, plus a durable interrupt()/Command resume that reaches your user on their phone.

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 and store for LangGraph.js

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.