Javascript agents

Womp scene API surface contract and model-facing scene functions for the LLM agent

VCR for LLM agent loops — record tool calls once, replay deterministically in tests

Official MCP server for the InternetData API. Lets an LLM agent browse the IP databases an organization is licensed for, inspect what is inside one, and verify a copy it already holds.

MarkdownScribe CLI — frontmatter, TOC, lint, format, mermaid and url-to-markdown from the terminal, built for humans and LLM/agent tooling.

Tenant and permission isolation for LLM agent tool calls: a principal context on AsyncLocalStorage, a guard that scopes every call and audits it, and a test kit that proves no tool escaped.

OpenTelemetry-native instrumentation SDK for LLM/agent calls (Iris) - TypeScript

Canonical IR types (ToolSpec, ToolSurface, Finding) for Toolsmith, a tool-surface linter for LLM agent tool definitions — see @alexvegman/toolsmith-engine.

Basic, app-independent tools an LLM agent can call: today's date and time, a place name to GPS coordinates, the distance between two points. No dependencies — the tool shape is structural, so any host that speaks the chat-agent-package Tool interface can

A terminal-based AI coding assistant. CodeYantram brings an LLM agent into your terminal — chat with the model, and let it read, search, edit, and execute against your project — all with full streaming, a built-in approval gate for anything that mutates,

Rubric-based eval harness for LLM/agent outputs, backed by the typesafe-ai/jev evaluation model via Vercel AI Gateway. Cheap enough (~$0.04/1M input tokens, one round trip per case) to run on every PR.

Record every boundary an LLM agent crosses: withRewind, the recorder, the redactor, and the stores.

dynamic-agents PoC: a bounded, event-sourced graph of LLM agent nodes

Read IXS ERC-7540 vault state, build unsigned vault transactions, and wire an LLM agent to propose them. No wallet, no keys, no hosted service.

LLM-friendly CLI for the Apple Search Ads API

Cross-script confusable detection, slug safety, and LLM Denial of Spend defence. Zero dependencies.

Additive request-field registry for the official DeepSeek LLM API adapter

Esedre: Developer roadmap, ticketing, and LLM coding partner coordination platform

Custom minimal ontology manifest for an executive agent operating on behalf of a software organization: 17 node types, 40 edges, warm-agent superset. Data-only.

Runtime-local LLM route tool-call projection metadata for DeepSeek Harness integrations.

Creates an http/s/socks proxy agent

MCP server, Agent Skills, and LLM files for coding agents using @craft-ts/core

Configurable DSH-native LLM verifier with a Web settings page

LLM Agent Relay Protocol: lets Claude Code and Codex sessions message each other without knowing each other's harness API.

Audit AI applications and agents for security risks before commit, PR, merge, or deployment. Deterministic findings with coverage and evidence receipts.

MCP (Model Context Protocol) client extension for the Pi coding agent — connect Pi to any MCP server

Mio Agent Runtime installer and MCP intelligence layer

n8n community node for Trendora Cloude: LLM AI, FFmpeg video merge, Voice TTS, Image FLUX, Video generator, Video Clipper, and Serverless Vector RAG Database

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

Persistent agent identity for AI agents — a hand-edited identity layer, nightly-distilled experience, and lessons injected every session, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, Pi, and opencode.

Build intelligent AI agents with TypeScript. The SmythOS SDK provides a powerful, developer-friendly API for creating agents with custom skills, workflows, streaming, vector databases, and state management - all with full type safety.

Ask LLM review, comparison, brainstorming, image, verification, and pairing workflows for Claude Code, Cursor Agent, and Pi

Hard stops + trailing stops + smart portfolio stops for Polymarket (PM has no native stops). Hard stop % / trailing stop % / daily loss / max exposure / portfolio kill (flatten all) from chain truth outside the LLM. Smart stops = trailing + portfolio kill

The deterministic trust layer for autonomous AI coding agents. Compiler-grounded verification of what an agent actually did vs. what it claimed, blast radius mapping, and persistent contract memory.

Enhanced MCP server for GraphQL with dynamic headers and robust variables parsing — a drop-in replacement for mcp-graphql.

Local-first Markdown memory runtime for Codex, Claude Code, and opencode. Hook-based capture, searchable project knowledge, and compact context.

Synerise base-context agent runtime with context management and native recovery

Workflow engine SDK — steps, triggers, executor, agents, and a framework-agnostic HTTP router.

Mobile remote control and local agent mesh for the Pi coding agent. Pair your phone via QR over a relay, watch tool calls in real time, run multi-Pi sessions over a local Unix Domain Socket broker, and let agents talk to each other through structured requ

Show the instruction graph your coding agents actually receive.

Fast, interruptible browser voice agent: VAD → STT → LLM → TTS with real barge-in, echo filtering, streaming first-sentence TTS and tap-to-seek. Zero runtime dependencies.

See through your agent's decisions. React components for debugging agentfootprint runs — messages, prompts, tool calls, decision scope, cost.

Public types, enums and options used by Llumiverse API.

LangChain JS tools for SIGDA — wallet-signed cross-platform agent messaging on Robinhood Chain. Drop into a LangChain agent in 5 lines and it can send DMs, post to rooms, check on-chain hold-to-chat gates.

The pre-trade safety net your LangChain agent didn't know it needed. Live sell simulation across every DEX on Base (Uniswap V2/V3/V4, Aerodrome), catching traps a static scan will never see. x402-powered.

NOT the latest Langfuse JS/TS SDK. Legacy v3 shared core — do not install directly. Current SDK: npm install @langfuse/tracing @langfuse/otel @opentelemetry/sdk-node

LangChain adapters for B4.run agents, chains, tools, streaming, embeddings, and retry.

Component discovery and agent setup for the Macaw Design System.

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.

Autonomous x402 web scraper tool for AI agents with automatic Base mainnet USDC micro-settlement

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

mnki — the Agent Trust SDK for TypeScript: give an agent an identity (keys + signed requests), guard() any tool call (local or hosted, observe → enforce), verify, delegate, attest, explain decisions, offline verification. Framework adapters as subpaths: m

DPX Protocol settlement tools for AI agents — LangChain and Vercel AI SDK adapters

A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Codex CLI, Kimi Code, DeepSeek Harness, Gemini CLI, MCP hosts and LangChain.

Chain of custody for AI agents: signed, independently verifiable receipts for tool calls. MCP gateway + Cedar policy + Merkle transparency log

Deterministic runtime evidence and diagnostics for LangChain TypeScript agents.

React components and usage guidance for the Macaw Design System.

LangChain.js adapter for ArtemisKit - Test LangChain chains and agents

Mizuki tools for LangChain and any JavaScript agent: quote, assess, and track fixed-price GitHub maintenance paid in USDC on Solana.

Framework-independent CSS design tokens for Macaw.

An http/s agent factory with proxy support

LangChain tool wrappers for TON Agent Kit

n8n community node for DeepSeek V4 models (deepseek-v4-flash, deepseek-v4-pro) with thinking mode control

LangGraph.js adapters and route contracts for B4.run agents, workflows, and graphs.

Serializable contracts for OwlMeans agents and LLM pipelines: conversation identity, the run lifecycle flow, and the record shapes an application persists.

LangChain.js tools for the AnswerLine answer and search monitoring API.

Embeddable AI chat widget built with Preact, Tailwind CSS v4, LangChain, and TypeScript. Designed to be dropped into any existing web page with zero side effects.

Independently versioned AgentCore Worker collaboration

LangChain.js integration for FoxNose — the knowledge layer for RAG and AI agents

Drop-in replacement for ChatGoogle that automatically fixes schema compatibility issues with MCP tools and Gemini API

Tembory Agent Memory for n8n AI Agents

Fail-silent OpenTelemetry tracing SDK for Matrix claim verification

RELKIT agent authoring API; prefer @relkit/app/agents in applications.

Type-only contract of the MindedJS agent model (flows, nodes, tools, state). Zero runtime dependencies.

LangChain chat model for Cursor models via the Cursor Agents SDK (local runtime)

Your model writes the code. This runs it where it can't touch your machine: a rootless Linux container, no daemon, no VM, no cloud, no account. A kernel boundary, not a microVM: for deliberately hostile code, use one.

Band TypeScript SDK core runtime

LLM inference runtime for OwlMeans applications: a resilient four-method model over any LangChain chat model, a provider-plugin layer, a model factory service, and an execution abstraction that resolves models from an inheritable policy.

Agenticrun client and LangChain integration for managed agent configuration and tracing

Scopebond framework plugins — one import so an agent checks your policy before every tool call and records a signed receipt. Cooperative (M0) in-process guard with Vercel AI SDK and LangGraph/LangChain adapters.

Adds /goal to pi: conversational goal planning, flexible or ordered goals, persistent progress, and an independent completion auditor.

LangChain.js tools for Sato Hub: search the scored onchain-agent index, run a Preflight check before installing or trading, get a swap-venue recommendation with the fee disclosed, and turn a goal into a build plan of real listings. Read-only and non-custo

OpenInference Instrumentation for LangChain.js Version 0.X

Agent Identity Management SDK for TypeScript/Node.js

Open auto mode for AI agents: a calibrated tool-call firewall powered by TypeSafe's Jev decision model (direct API, OpenRouter Decisions API, or Vercel AI Gateway). Ships as a Claude Code PreToolUse hook.

LangChain.js adapter for token-budget: BaseMessage[] conversion and a TokenBudgetMemory class — context window and token budget management for LangChain agents.

TypeScript/Node.js SDK for building Gjallar Protocol compatible agents — wire-aligned with the Python `gjallar` package.

Universal memory system for AI agents - CLI + MCP server + library API

A RAG chat library built with LangChain

Convert LangChain tools to Rejelly ToolDefinition for @rejelly/core

CLI and agent skills for managing GitHub PR review comments. List, filter, reply, and watch for bot findings.

LangChain.js integration for the turbopuffer vector database

Unofficial LangChain.js port of langchain-postgres (Postgres/pgvector integrations for LangChain).

LangChain integration for Bluebag

Bridge that lets an OpenAI agent (Chat Completions tool-calling) discover and call tools exposed by one or more remote MCP servers.

Open-source-safe CLI for persona simulation, observer review, and public-safe feedback drafts.

A composable agent loop that wires Armorer and Conversationalist into the standard agentic cycle. Includes provider subpaths for Anthropic, OpenAI, and Gemini (dynamically imported — zero-SDK-if-unused).

Parallel web search and extract tools for Mastra agents

Embed Archstone capabilities directly in your own agent loop: typed tool definitions for Anthropic, OpenAI, Gemini and plain JSON Schema, plus fail-closed execution over a compiled IR — no MCP server process required.

Deterministic runtime evidence and diagnostics for direct OpenAI Agents SDK integrations.