Agents
50 agents available in the ChatGPT directory
@sema-agent/core
Stateless, task-oriented AI agent core
@blockrun/clawrouter
Smart LLM router — save 85% on inference costs. 55+ models (8 free), one wallet, x402 micropayments.
@guangnao/agent-cli
AgentOS terminal CLI — drive a real LLM agent on the microkernel; strongest-UX shell, advanced agent core
@tangle-network/agent-app
Application-shell framework for Tangle agent products: a bounded tool loop, the structured agent→app tool side channel, integration-hub client, per-workspace billing, and crypto — composed over the Tangle agent substrate through typed seams.
ai
AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.
@earendil-works/pi-coding-agent
Coding agent CLI with read, bash, edit, write tools and session management
@earendil-works/pi-agent-core
General-purpose agent with transport abstraction, state management, and attachment support
@earendil-works/pi-ai
Unified LLM API with automatic model discovery and provider configuration
@mastra/agent-builder
This package is currently experimental and only meant to be used internally to Mastra at the moment, the APIs are subject to change in this period.
@mastra/core
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
orquesta-cli
Orquesta CLI - AI-powered coding assistant with team collaboration
@langchain/core
Core LangChain.js abstractions and schemas
@duetso/agent
An opinionated full-stack agent turn runner with native memories, interrupts, and multi-agent orchestration
agents
A home for your AI agents
@silverprotocol/core
AgJSON core — the typed schema (AgInput / AgEvent / AgMessage), the Normalizer interface, and the normative reduce().
@agentskit/runtime
Standalone agent runtime with ReAct loop for AgentsKit.
@kitpilot/cli
KitPilot — a model-agnostic CLI AI coding agent. BYOK by default, with an optional bridge that borrows GitHub Copilot from a running VS Code host.
nexus-cortex
A headless, multi-provider AI agent harness. One install gives you the cortex CLI and HTTP server: npm i -g nexus-cortex.
@langchain/openai
OpenAI integrations for LangChain.js
langchain
Typescript bindings for langchain
nexel-cli
An AI coding agent that lives in your terminal — it reads, edits, and runs your code to finish real tasks, asking before it changes anything. Start with one Nexel access key (no model setup) or bring your own OpenAI, Anthropic, or Azure key. Streaming rep
@metaharness/darwin
Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold
@opentelemetry/instrumentation-openai
OpenTelemetry instrumentation for the openai OpenAI client library
memory-working-agent
MWA — Memory Working Agent. A turnkey TS agent runtime built on AWM as an always-on cognitive substrate, so a cheap model conducts, resumes, builds on prior reasoning, and runs long without re-onboarding or context rot.