Javascript agents

Ultra-lightweight, scalable CLI/TUI coding agent optimized for tiny local models & remote runtimes

Pi-native OpenAI Codex subscription model provider plugin for Assembly Line.

Paperclip adapters for Hermes Agent local CLI and Hermes Gateway HTTP/SSE runs

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

Configured coding agents and isolated Cursor, Claude Code, and OpenAI Codex sessions

An OpenAI compat integration for Effect

A TypeScript framework for building interoperable AI agents

An OpenAI provider integration for Effect AI SDK

OpenAI model provider plugin for Assembly Line's Pi harness.

Run AI coding agents (Claude Code, OpenAI Codex, GitHub Copilot CLI) inside Docker against a dedicated Git worktree.

Compress LLM tool output, reduce context tokens, and recover lossy originals from a local stash.

Official Node.js/TypeScript SDK for Moda — the continual learning layer for AI agents. Automatic conversation threading and OpenTelemetry-native tracing.

Self-hosted LLM gateway and SDK for Node — a LiteLLM-style unified API for 13 providers (Anthropic, OpenAI, Gemini, Mistral, Groq, xAI, DeepSeek, OpenRouter, …) with per-call USD cost tracking, streaming, tool calls, vision, speech-to-text, and built-in O

One safe, offline health check for the coding agents installed on your machine.

Local-first OpenAI-compatible gateway and control plane for an authorized Postman web session.

Personal LLM API gateway & proxy — one address + one API key for all your models. Forwards OpenAI & Anthropic calls to your backends with failover and a circuit breaker. Pure passthrough, no format translation. Self-hosted (CLI + web UI).

Klyro — autonomous coding harness CLI that streams from any OpenAI-compatible or Anthropic LLM endpoint.

Agent-first facade for the Zhivex AI SDK runtime.

MCP server + client for cross-platform desktop control (macOS + Windows + Linux) — screenshot, mouse, keyboard, clipboard, app management. Backed by Rust NAPI native module.

TypeScript SDK and CLI for Codex Security

A minimal coding agent CLI built to learn agent harness architecture.

VTX Macro CLI, MCP server, and durable external inference host.

Schema-first APIs for text, images, video, speech, and transcription, built with Effect.

A voice agent that runs on your own machine — talk to her, she hands the slow work to bots with a shell, a browser and skills.

Provider-neutral connector SDK for Showrunner agents

Convert DeepSeek Web Chat to an OpenAI-compatible local API and interactive CLI for any harness or agent

Interactive coding agent (Pi) with UiPath LLM Gateway and BYO provider support.

Portable, model-agnostic agent workflows for any codebase

Tool loop and model providers (bring your own key)

Deterministic runtime evidence and diagnostics for direct OpenAI SDK integrations.

Self-hosted Anthropic- and OpenAI-compatible API backed by your signed-in coding-agent CLIs, plus a zero-config library for driving them from your own apps — no API keys needed.

One agent. Every surface. Your rules.

OpenAI-compatible model provider - raw fetch + SSE streaming, zero AI SDK, retry/backoff with ERR_UPSTREAM_* errors

Navarch machine-side session manager: claims delivery tasks and runs them through local coding agents.

Vesk agentic plugin — zero-deps agent loop, provider abstraction, permissions, tools, checkpoints

TokenRouter.com unified API gateway as a native Pi provider for accessing 300+ LLM models via a single API key

A lightweight runtime that unifies 110+ AI providers behind a single, OpenAI-compatible API.

KajiCode — a fast, multi-provider terminal coding agent.

YuanGe (元阁) — orchestration and routing for the YottaMeta skill family, packaged as a YottaMeta Agent Plugin.

A coding-agent CLI that works the same way whether the model is Claude, GPT, or an open-weight model like Qwen, DeepSeek, GLM, or Llama running locally.

A TypeScript library for managing AI conversation state

pi provider extension backed by @cursor/sdk local agents

Retrieval-Augmented Generation for nestjs-agent — chunking, ingestion, an embedding-backed Retriever, and in-memory + pgvector stores

Unified LLM API with automatic model discovery and provider configuration

Language-neutral protocol artifacts for the Sogni ecosystem: tool schemas, prompts, OpenAI tool manifests, and enums. Consumed by every Sogni SDK (TypeScript, Swift, and future Python/Kotlin/Rust SDKs) so contracts stay in lockstep across languages.

Twilio Agent Connect - A TypeScript framework for building intelligent agents

Yuanyi (元忆) — boundary-aware, file-based memory for AI agents, packaged as a YottaMeta Agent Plugin.

AgentRouter provider for pi — GPT-6 Astra, GPT-5.6 Sol, Claude Opus 4.8/5, DeepSeek V4 Flash and GLM 5.3 under one namespace, with self-healing WAF recovery (history redaction + auto-translation)

hncode — A cyan-blue TUI AI coding agent with zero runtime dependencies.

Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.

The endpoint-agnostic half of an OpenAI-compatible agent loop: tool-schema compatibility, on-demand tool loading, one-shot side tasks, run events, and a pooled client.

Connect an AI coding agent to Beeline with one command.

Gu CLI — the gu terminal plus the local worker that runs agent / OCR / PDF / embedding jobs on your Mac (Ollama / MLX / OpenAI-compatible).

Web search and fetch with configurable fallback order across OpenAI, Exa, Tavily, Firecrawl, Monid, Ollama, and direct HTTP.

The agent loop, tool execution, context management and permissions. No frontend, no transport.

Model-aware NVIDIA NIM reasoning compatibility for the pi coding agent

Felan Code: an open-source, model-portable coding agent built for cost-efficient, verifiable software work

Model Context Protocol (MCP) server for AI-assisted development of CAP applications.

AI SDK by Vercel - The AI Toolkit for TypeScript and JavaScript

Secure OpenAI Key Proxy (SOAKP) facilitates secure usage of the OpenAI API key through a proxy-like application.

n8n community node to call the Langdock API: send messages to Langdock Agents, run OpenAI-compatible chat completions across providers, and create text embeddings.

ChatGPT/Codex runtime for Stratus Agent: runs turns through the OpenAI Codex harness with kernel tools served over a loopback MCP endpoint

Unified LLM API with automatic model discovery and provider configuration

Phone approvals for OpenAI Agents SDK agents. Your agent asks, your user taps Approve or Deny.

通用对话式 Agent 执行引擎：OpenAI Responses / Anthropic Messages 双协议 + Agent loop + 文件工具 + 可选 REST/SSE 服务层

Autonomous agent factory — loop runner and worktree engine.

Glintbase Agent Harness — autonomous agent-readiness auditor (ARS 3.0), Flight Simulator & CI drift shield

Client library for participating in the Epistemic Resonance Protocol as an autonomous agent

Tamper-Evident Autonomous Agent Action Audit & Governance Logging MCP Server

Deterministic policy engine for autonomous agent tool enforcement

Durable six-column taskboard and autonomous agent work queue for DSH

Model Context Protocol (MCP) server providing the universal autonomous agent runtime interface, execution lifecycle state machine, and resource budgeting.

DeepSeek Harness native macOS desktop app, background daemon, and autonomous agent environment manager

Time-Machine-backed autonomous agent permission gate for DeepSeek Harness (dsh). Allows TM-rollback-able operations, blocks everything else.

Official TypeScript & JavaScript SDK and CLI for Shivanshu Tiwari Portfolio APIs, projects, and autonomous agent evaluation

MCP server that gives an autonomous agent its own Ethereum wallet. The keys stay on the agent's machine.

Give your autonomous agent its own Ethereum wallet. Creates the keys on this machine and adds nyquist-mcp to your agent.

Dual-tier client library for Autonomous Agent-to-Agent (A2A) micro-utilities with x402 V2 gasless micropayments

Every provider. One terminal. Agentic coding CLI with MCP, skills and plugins.

Nexora — One Agent. Any Model. Any Workspace. (Terminal CLI)

Autonomous terminal agent harness engineered to understand software tasks, conduct web research, reflect on tool plans, safely modify codebases with automated verification, execute commands in Docker, enforce safety guardrails with secret scanning, and re

Autonomous Security Intelligence & Competitive Exploitation Framework

Autonomous AI Accountability Coach & Execution Agent for the Terminal

Strategic BDI reasoning engine for autonomous AI agents — goal decomposition, utility scoring, risk evaluation, and reactive replanning over PuterVision memory and world models.

The ultimate penetration testing agent

/ship takes one sentence to verified code. Terminal coding agent for DeepSeek and any OpenAI-compatible endpoint. Zero-dependency launcher for the DeepSeek Harness.

Cross-platform CLI and MCP cognitive runtime for AI coding assistants

AI coding CLI powered by OpenRouter - Free and open source

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1700+ vulnerability rules with AST & taint analysis, LLM-powered semantic code review, auto-fix. For Claude Code, Cursor, Windsu

A deterministic context compiler for AI agents — evidence-driven context engineering beside your markdown knowledge base: agents propose, evidence gates, you decide.

Local-first governed tool execution gateway for AI agents. Read/write classification, policy evaluation, signed execution receipts, multi-key rotation with cross-signed chain snapshots, per-capability rate limits, threshold-based escalation, file/webhook

MCP server for AIProx — the open agent registry. Discover and hire 24 verified autonomous agents by capability. Model selection passthrough: specify any of 19 LightningProx models per agent call. Supports Bitcoin Lightning, Solana USDC, and Base x402.

Authenticated MCP agentic runtime with signed skills, persistent model backends, identity-bound remote devices, durable job supervision, immutable release slots, and separately revocable machine authority.

Open-source pre-execution risk gate and prompt injection guard for AI coding agents (Claude Code, Codex CLI, opencode, pi, oh-my-pi, Hermes): local rules, optional TypeSafe Jev (System One) or local Laya judgments, an editable policy, System 2 escalation

This extension is designed for one purpose: to capture a session’s continuation context more precisely than compaction and pass it to a fresh, natively linked Pi session as the first prompt that starts the replacement. How work continues is determined by

bgc — the official Bitget shell CLI for the Unified Trading Account (UTA / v3) API. Drive market data, trading, positions, account, funds, loans and tax from your terminal or a shell-based AI assistant (Claude Code, Codex CLI, OpenClaw) via intent verbs,

Run AI coding agents in isolated sandboxes

Enterprise AI Security, GrokBot & Agent Runtime Firewall, In-Process Guardrails, Zero-Trust MCP Proxy & Reversible PII Vault SDK by AcadmyAI

IUMBTEMS (Epistemic Swarm) — High-Integrity Dialectic Research Agent Harness for Claude Code, OpenCode V2, Pi (pi.dev), OMP (oh-my-pi), Gemini CLI, Codex CLI, and AntiGravity

Core SDK for TON Agent Kit: plugin system, wallet abstraction, agent class