Autonomous AI agents that perform tasks independently
caupulican
Unified LLM API with automatic model discovery and provider configuration
reaatech
Provider-agnostic speech-to-text interface with Deepgram, AWS Transcribe, and Google Cloud Speech-to-Text adapters
wakita181009
Firestore-backed SessionStore for the Claude Agent SDK
Francesco Marchesini <[email protected]>
Orchid — platform-agnostic multi-agent AI framework (LangGraph + RAG)
SUSATest <[email protected]>
Local agent for SUSATest — connects your Android or Windows device to the cloud testing platform
Trinity Contributors
Three minds, one context — Multi-agent AI orchestrator for Claude Code, Codex, and Gemini CLI.
pytest-compatible test harness for AI agents — deterministic record & replay for Anthropic Claude
cybernandan
Schemas and types for the Lodestar epistemic chain. Part of Lodestar, the trust layer for AI agents.
raskhaaa
Reputation oracle for onchain AI agents on Base. ERC-8004 + x402, with activity, recency, reputation, health, longevity scoring.
...moreagentloop contributors
A minimal, reusable Python framework for building LLM agents with tools and an observe-act loop.
bbvch-ai
The open-source AI infrastructure stack for Swiss enterprises.
yeheskiel
TypeScript SDK for the Claudelance bounty marketplace on Celo. Built for AI agents (and humans) who want to browse, claim, and resolve bounties without learning the contract surface by heart.
...moregcontext — file-based knowledge protocol for AI agents
ieepirzy <[email protected]>
YAML-defined agent orchestration framework powered by PydanticAI
AI Role 树 — 约束 LLM 防致幻（Role / Policy 唯一源码）
Samuel Kalu <[email protected]>
Du-RAG: Durable RAG — persistent memory for AI agents
lambdatestdev
n8n verified community node for TestMu AI (Formerly LambdaTest). Gives an AI Agent native browser tools — navigate, click, type, extract — running on TestMu's real cross-browser cloud infrastructure via the W3C WebDriver protocol.
...moreNous Research
AI Agent Security Scanner — detect tool-calling vulnerabilities in LLM agents
Berkay Turancı
Cross-vendor multi-agent PR review jury — orchestrate native coding-agent CLIs (Claude Code, Codex, Antigravity) to mutually review and debate the same pull request.
...morePython SDK for H Company's Agent API: autonomous agents powered by Holo.
GitHub Actions
Token efficient IDs for AI agents. UUID alternative for the agentic era
Luca Benedettini
Frictionless Salesforce Agent Skill for Codex, Claude Code, and GitHub Copilot.
Instrument LLM clients and emit usage events to Lago.
algoexperthub
1282 production-ready AI agent skills with self-evolving meta-skills — cybersecurity, SEO, trading, marketing, automation, devops, content, financial services
...more