Javascript agents

In-process spawn subagent backend: runs a fresh child agent on ctx.agents

Spec-driven development for LLM coding agents: 9 skills + a stdlib evidence engine. Facts block, guesses advise; the human approves.

DeepSeek-backed search provider (native web_search via the Anthropic-compatible API) for the DeepSeek Harness web capability seam (ctx.web)

Write and backtest trading strategies against a multi-agent AMM token market with liquidity and vesting.

pi-ai-backed DeepSeek adapter for the DeepSeek Harness LLM seam (design-verification twin of dsh-llm-deepseek)

Event-sourced session store for the DeepSeek Harness

DeepSeek chat-completions adapter for the DeepSeek Harness LLM seam

Curated schema.org warm-agent ontology manifest for LLM Wiki Memory: 9 node types, 28 edges, fully schema.org-standard. Data-only.

Vitest plugin for the vitest-agent ecosystem: owns persistence, classification, baselines, trends, and dispatches rendering to a configurable reporter.

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

LLM-agnostic AI platform for SAP CAP. 11 providers behind one API (Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Ollama, Groq, Fireworks, DeepSeek, Mistral, OpenAI-compatible, SAP Generative AI Hub) with 30+ middleware primitives spanning cost/resi

See exactly what your AI agent did. Lightweight tracing + a local dashboard for debugging LangChain agent runs.

Core utilities and types for Gaunt Sloth

LangChain integration for SmartAgentKit — AI agent smart wallet tools

Custom n8n OpenRouter Chat Model sub-node with JSON options support (reasoning, max_tokens, etc.) for use with AI Agents and Chains.

Agent runtime for Gaunt Sloth: tools, middleware, MCP/A2A clients and the AG-UI server

Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).

Kojiru Recourse Layer™ tools for LangChain — plug-and-play credit primitives (ACS™, stake, slash, draw, anchor, records) as native LangChain StructuredTools.

OpenAI-compatible HTTP server over ACP agents. Use Claude Code, Codex, opencode or any ACP CLI from anything that speaks the OpenAI API but does not speak ACP yet.

ThinkHive SDK v4.0 - AI agent observability with business metrics, ROI analytics, and 25+ trace format support

Agent interface, registry, initiator scope, and event vocabulary for the DeepSeek Harness

Per-session agent composition from preset cordis.yml files for the DeepSeek Harness

Reusable wrapper of langchain

Langchain integration with endee vector database.

Agent-plane presentation selector: composes one agent's tools as Code Mode, native, or both

An x402-gated web scraper tool for LangChain agents, powered by Algorand.

Composition-authored deployment persona section for the DeepSeek Harness

API gateway: the ApiProxy contract (api/), the fetch carrier pair (fetch/), and the host-side gateway plugin providing ctx.apiProxy

## Overview

ACP adapter for pi coding agent

A lightweight OpenAI agent harness with tools, builder API, and a ReAct-style JSON pipeline.

Local-first, single-user general agent for the command line.

Local x402-paying proxy + MCP server for openzoo.fun — point any OpenAI-compatible harness (Cursor, Claude Code, aider, SDKs) at localhost and it pays per call from a local burner wallet. Solana and Base rails live; Robinhood experimental. `openzoo build|

The universal config-driven Guuey worker. Reads the resolved agent.json snapshot, runs the Claude Agent SDK, and emits each native SDKMessage to fd-3 as a `native` WorkerEvent.

Vercel AI SDK agent runner for Pikku

Zero-config agentegrity adapter for the OpenAI Agents JS SDK (@openai/agents). Mirrors the Python agentegrity.openai_agents module.

NestJS-native framework for building enterprise-grade, governance-backed AI agents.

OpenAI provider for chai-ai.

Codex CLI-backed agent adapter for alint

Open-source schemas + loaders for the three guuey config files: agent.json (declarative agent definition), guuey.json (hosted-deploy overlay), and the helper types around them. Consumed by @guuey/cli, the guuey backend, and devs writing their own agent or

Minimal Pi extension for OpenAI Fast mode.

This is the OpenAI provider for the Rabbit Agent SDK.

Statsig helps you move faster with feature gates (feature flags), and/or dynamic configs. It also allows you to run A/B/n tests to validate your new features and understand their impact on your KPIs. If you're new to Statsig, check out our product and cre

Turn one approved plan into a team of AI coding agents that build it in parallel, in isolated git worktrees, from inside your editor.

Natural-language CAD drawing agent for [cad-viewer](https://github.com/mlightcad/cad-viewer).

n8n community nodes: Standalone AI Agent with multi-provider LLM support and integrated Langfuse/Phoenix/Helicone observability

Improve OpenAI in pi with fast mode, usage stats, realtime voice, image generation, and footer polish.

Vite plugin for packaging OpenAI Sites deployment metadata.

AgJSON normalizer for the OpenAI Agents SDK (RunItemStreamEvent / Responses streaming → AgEvent[]) — fixture-tested.

OpenAI-compatible chat completions provider adapter (OpenAI and any compatible endpoint) with streaming and tool calls.

EU-hosted AI coding agent with Ink TUI, tool execution, skills, slash commands, and plugins. Mistral La Plateforme by default. Your code stays in Europe.

OpenAI model provider adapter for @purista/harness.

Runtime control, proof, and fleet intelligence for MCP-compatible AI agents.

Declarative provider, model, connection, and secret composition for Clear Ideas Agent Runtime.

通过 Web 操作本地 Coding Agent 的应用

MCP server for summon-agents: dispatch an approved plan to parallel AI coding agents from Claude Code, Cursor, or VS Code.

TypeScript SDK for Browser Agent

Headless library for building control loops: scheduled bots that scan a repo for a class of anomaly, fix a few instances with a coding agent, and open a PR — no server, UI, or persistent process.

OpenAI SDK adapter for llm-ports. Implements LLMPort and EmbeddingsPort. baseURL support covers 10+ OpenAI-compatible providers (Azure, Groq, Together, Fireworks, DeepInfra, Perplexity, Cerebras, LiteLLM proxy).

A requirements-led, task-driven workbench for secure autonomous Agent delivery

Deterministic spend-authority engine: decides whether an autonomous agent may spend, before any money moves.

SelfAgent — Cross-platform Autonomous AI & WhatsApp Gateway Agent. Install once, chat from your terminal or WhatsApp. Secure key storage via OS keychain (Windows DPAPI, macOS Keychain, Linux libsecret).

Gemini-powered self-serve commerce agent with local encrypted wallets, multimodal procurement, negotiation, self-healing, and AIFP-1/x402 payments.

ANTRI Code - The Autonomous Agentic CLI & Desktop Assistant

Autonomous AI coding agent — explores your codebase, diagnoses root causes, writes fixes, and runs tests. Supports Claude, Gemini, DeepSeek, and Kimi K2.

Autonomous AI coding agent CLI powered by 9router with full Antigravity experience

iOS-native-feeling responsive React select with a keyboard-aware mobile bottom sheet, virtualized rows, and multi-select draft/commit.

Client audio capture, host transcription, and autonomous narration for Pi agents.

Deterministic spend-authority engine: decides whether an autonomous agent may spend, before any money moves.

Model-facing same-session goal tools with execution-time authority checks

AI agents (Spores) that autonomously manage X/Twitter accounts

Replay-aware token measurement service (ctx.tokenMeter) for the DeepSeek Harness

The dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layer

Rendobar SDK: TypeScript client for the media processing and AI generation API.

Whole-log conversation counts and wall times projection (sessionStats) for the DeepSeek Harness

Lifecycle-bound per-message rating and note sidecar for the DeepSeek Harness

Per-message feedback controls contributed to the assistant-message action strip, backed by the messageFeedback Host Remote

Trajectory event ledger with an interactive timing overview: pure-consumer plugin registering into the conversation ViewMap (no service)

In-process fork subagent backend: runs a child agent seeded with a prefix of the parent's log

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

JSONL durable session persistence backend for the DeepSeek Harness

Shared in-process subagent run driver: drives a child agent on ctx.agents (used by the spawn and fork backends)

A modern, responsive AI chatbot widget for websites

Cross-session snapshot references and durable untrusted model context (ctx.sessionReferences)

_This package is **experimental**._

OpenTelemetry backend for the DeepSeek Harness telemetry seam: hands captured session records to the OTel JS SDK's log pipeline

Provider-neutral AI contracts for AgentProdReady — execute, stream, tools, and embeddings without vendor lock-in at the boundary.

Stdio JSON-RPC server plugin for out-of-process DeepSeek Harness SDK clients

@ai-sdk/anthropic with all dependencies updated to latest

Telemetry seam for the DeepSeek Harness: session-event capture, projection, redaction, and handoff to a reporting backend

An open source low-code development platform

SDK and CLI for iLiveMyLife Knowledge Graph

Universal headless AI Assistant engine with extensible tool execution and custom relay support.

Smart dev server launcher: error→AI search, success→auto-open browser. Any CLI tool.

TAKT v2 CLI — multi-agent production system

Multi-agent orchestration, sub-agent delegation, parallel execution, and iterative refinement loops for nestjs-agentic.

AgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI

TGO — a thin multi-agent orchestration plugin for OpenCode

AI-powered multi-agent Playwright test framework generator

Multi-agent workflows with full observability and time travel: watch every step live, rewind, fork, and replay any run. Claude Code, Codex, Gemini, Hermes, OpenClaw, any model or harness.