Autonomous AI agents that perform tasks independently
prxg22
A small, publishable client for the **agent-api** sandbox execution path. It owns the HTTP contract so consumers (tela, chat-app, tela-dock) don't re-implement the execute request, the SSE session parser, and `vault://` reference resolution by hand.
...moreUnstruk Data Inc.
Top-level Graphlit tool factories for TypeScript streamAgent applications
CryptoSuess & Txnchi
The Operating System for AI Security — monitor, secure, and audit every AI agent and LLM application in production.
Live, verifiable data tools for AI agents — Dynamic Feed client + ready-made adapters for LangChain, CrewAI, LlamaIndex and Pydantic AI.
...morePaul le Cimanova
SportAgent: Multi-Agent LLM framework for Kalshi sports markets
vixyz
Self-hosted runner for forked.online pods — registers with the platform, clones a workspace's repos onto a persistent volume, injects env vars, keeps a tmux session, and heartbeats. Honors the platform's manual on/off.
...morezowie
Node.js/TypeScript SDK for building external agents that integrate with Zowie Decision Engine
fabkho
Toolkit for managing i18n in any framework
Owl-Listener
An agent design team you control: 10 agents that run an inclusive design process while you direct.
a2z2k26
Modular agent infrastructure primitives for orchestration, memory, routing, cost tracking, and AI system operations.
phronesis-framework
Phronesis is a Python framework for designing, composing, and operating AI agent systems - typed, observable, and built for production. Agents have episteme (knowledge) from the LLM; Phronesis gives them phronesis (practical wisdom).
...moreTemporal Technologies Inc. <[email protected]>
Temporal OpenAI Agents SDK integration package
AgentSIM <[email protected]>
AgentSIM Python SDK — autonomous OTP relay for AI agents
Graphlit
Python SDK for the Durable Agents public API.
PlaiPin
AgenticROS core — platform-agnostic ROS2 transport, types, and config (the dep every AgenticROS skill imports).
Agent execution harness — wraps LLMs in structured, inspectable workflow specs
agent-relay contributors
Chain any AI coding CLIs (Claude, Codex, Gemini, Aider, ...) into an approve-once pipeline.
EMILIA Protocol
EMILIA Protocol guard for LangChain tools: a named human approves the exact irreversible action (Face ID / passkey) before it executes — fail-closed, with offline-verifiable Trust Receipts.
...morekanakawai-maui
CLI tool and web dashboard for spawning and managing parallel agent worker processes in a tree structure
Atharva Sehgal <[email protected]>
Wrap installed coding-agent CLIs; capture traces, curate cross-session knowledge, serve a read-only viewer.
mikecookcbh
Playwright reporter that outputs structured JSON for LLM agents. Minimal console output, flat schema, easy to filter to failures.
...morersd-raindrop
Raindrop integration for OpenAI Agents SDK
jackiejuju
Neural-network-inspired memory engine for AI agents. OpenCode plugin with Hebbian learning, spreading activation, associative recall, LLM/embedding enhancement, and multi-machine sync.
...moreMoritz
Earned autonomy for the OpenAI Agents SDK — warrantd drives the approval switch.