Javascript agents

Core framework for building LLM agents: plugin-driven Agent runtime on the official OpenAI SDK, Messages, Tools

OpenAI text-embedding provider for brain-core (inference-plane EmbeddingProvider)

Groq adapter for @warlock.js/ai (OpenAI-compatible, thin wrapper over @warlock.js/ai-openai)

oFlow CLI - AI-powered terminal assistant for developers

Cache-first DeepSeek coding agent for the terminal.

ClinePass provider for pi — access GLM-5.2, Kimi K2.7, DeepSeek V4 and more open-weight coding models through Cline's $9.99/mo subscription

A drop-in replacement of the official `OpenAI` client for sending events to Libretto.

Loom Code — AI-powered coding agent for the terminal. Multi-provider support including NVIDIA. OpenTUI interface.

CLI coding agent with OAuth authentication for Anthropic, OpenAI, and Gemini

OpenAI SDK adapter for Crux — run Crux prompts and agents against OpenAI models.

Use a ChatGPT Codex subscription in DeepSeek Harness through standalone OAuth

Lightweight coding agent with selectable restricted or native workspaces and optional remote executors.

The OpenAI Agents SDK (TypeScript) adapter for Welt's wire contract.

Local-first CLI for connecting coding agents to Dharma evaluation, orchestration, and signed Skill delivery

The security-native AI coding agent. Six Sec-Test security personas, compliance-first /scraper, a business documents & research suite, and multi-agent Compose orchestration — spec-driven workflow engines in one terminal-first CLI.

quantum-spherifier (:qSpherifier) v1.0 — Autonomous Scientific Research Agent for Quantum Computing. Built on the Artificial Junky Neuron (AJN) framework, extended from predator-jungle-agent v2.0 via fusionary-agent by Justo Tapiador Garcia (UA). Generate

ToolNet CLI — AI coding agent for the terminal

43 Product Design Agent Skills for AI coding agents. Covers Visual Intelligence, Product Thinking, UX, UI/Design Systems, Modern Platform Patterns, Responsive, QA Autonomous (incl. UX Chaos Monkey stress testing), and Growth-Aware workflows. Compatible wi

OpenCode goal plugin for persistent autonomous multi-turn coding agents with host-verified completion, restart recovery, and /goal workflows.

Codex-inspired background goal engine for OpenCode — autonomous subagents, engine-driven loop, child worker sessions and modal TUI dashboard. Like Claude Code loop for OpenCode.

ICOA CLI — AI-native competition runtime of the International Cyber Olympiad in AI: learn, practise, and compete in AI & cybersecurity from the terminal (AI4CTF · CTF4AI · CTF4EAI)

Shared wire protocol for the DeepSeek Harness SDK runtime: the newline-delimited JSON-RPC stdio transport and the named request, result, and notification types spoken between the runtime server and SDK clients

Fast, provider-agnostic AI coding assistant — BYOK, any provider, all from your terminal.

Remote multi-agent workspace CLI with deep Claude integration, native terminal streaming, and self-hosting.

Multi-agent team management plugin for DeepSeek Harness

Eko multi-agent connector for BonkLM — validates planner output + BrowserAgent + FileAgent + MCP-tool dispatch.

Deep Ideation, Multi-Agent Deliberation & Systematic Thinking Engine for AI Coding Agents

Rose: The Advanced Agentic Coding Assistant, platform with tools, memory, automation, research, multi-agent orchestration and Gemini Live.

Mnemo-backed long-term memory for LangGraph JS — a BaseStore implementation plus remember/recall tools.

Live terminal debugger and offline ASCII graph renderer for LangGraph.js — no LangSmith account, no network calls.

Ship agent traces from OpenAI Agents, Claude Agent SDK, LangChain, LangGraph, Vercel AI SDK, n8n and any OpenTelemetry-instrumented agent into Cognipeer Console.

Optional exact and semantic answer-cache primitives for Inupedia Spotlight

Watches the third-party APIs a codebase calls and opens verified pull requests when one breaks. Docker if you have it; a user-space install if you do not.

Baize (白泽) — autonomous AI agent infrastructure

Cyber-first freestyle local AI agent

CLI to install, update, and manage modular AI agent skills for Wangs UI React applications

Enterprise Autonomous Multi-Model AI Agent Gateway Engine

Self-improving AI agent CLI with evolution capabilities

Local-first coordination for independently opened AI agent sessions.

Shiplens CLI - Automated Web User Analytics & AI Agent Analysis Engine (Native Go Runtime)

n8n community nodes for CIPP.app automation and AI-agent tooling

Official command line interface for the Box API. Includes official AI agent skills: box/box-for-ai.

AI agent that streams JavaScript into a persistent sandboxed Node.js runtime

Next.js and Python AI agent starter with tools, streaming, structured output, and jobs.

Local-first AI agent memory system. No account needed.

Upload local AI agent sessions to turns.dev

Cadet Token Saver — an orchestration + measurement layer that reduces AI-agent context consumption.

科豆 AI Agent CLI —— 基于 @kedouai/agent-core 的交互式 AI Agent（自带大模型 API key，不消耗作者 token）

Local A2A gateway for waking AI agent runtimes

Terminal UI binary for the Real Memory AI Agent CLI (darwin/x64).

Audit and prune unused AI agent skills, MCP servers, hooks, and agents

Server-side analytics for AI agent traffic

Optional provider-replaceable AI agent orchestration runtime for Asyra

Local, observable computers for any compatible AI agent

CLI initializer for Manggala Backend Golang AI Agent Skills

Audit AI agent skills folders for problems that fail silently

AETech Labs AI Agent Core — encrypted, license-protected agent orchestration engine

AI-agent-first CLI for Motadata ObserveOps (AIOps) observability platform

AOV AI Agent - Monorepo for AI Assistant Components

PowerPoint-faithful React PPTX editor and viewer — full OOXML fidelity, real-time human + AI agent collaboration.

让任意 AI Agent 直接调用 focalapi 创作模型的命令行工具

Standalone, multi-provider AI agent tools library in plain JavaScript

Agent Behavior Specification — describe, run, and evaluate AI agent interactions from the command line

Reusable AI agent chat UI library for Angular

AI agent runtime security: context-preserving tokenization, risk scoring, and policy enforcement

AI Agent node for n8n with automatic multi-model failover and retry mechanisms

CAITLYN Security Guardian Agent — interactive defense agent for LLM agent protection

NewBeeDebugBridge 工程师端 CLI —— 远程运维(截图/执行/读文件)，对 LLM Agent 友好。

Typed framework for durable LLM agents: pipeline builder, FSM engine, durable checkpoints, and adapters for headless CLI providers (Claude Code, Codex CLI)

Robodev server SDK — defineDatabase, defineApi, defineMcpTool, defineMcp, defineJob, defineSocket, defineAuthHook, auth, email, llm, agent, storage, pdf, push, and the injected Drizzle db

Defensive LLM agent honeypot chat widget - traps nefarious AI agents into burning their own tokens. Client-side, Cloudflare Workers, or full backend.

GPT 专家模式：让免费/低成本 LLM agent 调用 ChatGPT 网页版作为决策主脑，无需 API Key。基于 parley CDP 框架二次开发。Use ChatGPT (web) as the decision brain for low-cost LLM agents, no API key needed.

AI news & hot topics panel for DSH: LLM / Agent / AI creation trends / AI hot topics / AI short-drama (manju), powered by DeepSeek web search with on-demand AI summaries

Runtime CSS probe — inspect layout, colors, backgrounds, fonts and more in a live browser. AI agents and shell automation.

OpenTelemetry OTLP Exporter base (for internal use only)

High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.

Provider-neutral LLM service interface for the DeepSeek Harness

Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.

JSON Schema definitions and TypeScript types for VAT agent manifest format

Production patterns for AI agent orchestrators — tool-calling loops, multi-stage pipelines with checkpoints, LLM provider routing with fallback, four-layer memory with confidence decay — plus the wallet side of reselling LLM access. This package is the in

Provider-routed LLM request retry policy for the DeepSeek Harness

Veryfront first-party extension package for ext-llm-google

Claude Agent SDK runtime adapter for VAT agents

Pi extension that uses Claude Code (via Agent SDK) as a model provider and adds an AskClaude tool.

Connect this machine to Ensemble — runs the local agent runner and wires the ensemble session messaging so your coding sessions talk (per-org, isolated).

General-purpose agent with transport abstraction, state management, and attachment support

Replay LLM plugin: short-circuits llm/stream with model chunks reconstructed from a recorded session JSONL (keyless snapshot tests)

An Antora extension to generate llm.txt files for LLM consumption.

Provider-routed LLM request retry policy for the DeepSeek Harness

Gate every LangChain agent action through Qerexa runtime trust enforcement.

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

Simple MCP Client to quickly test and explore MCP servers from the command line

MemorySync integration for LangChain.js and LangGraph.js: chat message history, memory tools, recall context, and a LangGraph store.

Metrik agent layer: x402 verified-streaming payments, an MCP server, framework tools, and spend mandates so AI agents can hire and pay verified services safely.

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

LangChain adapter for textopt

A Linux-like container that runs entirely inside Node.js — POSIX shell, ~140 coreutils, Node.js and Python runtimes, virtual filesystem and networking. No Docker, no VM, no native modules.

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

TypeScript SDK for FerricStore and FerricFlow

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