Autonomous AI agents that perform tasks independently
Declarative squad-based Multi-Agent System (MAS) collaboration framework for AGAPES
Hmzbo
Deep Agents sandbox backend for a locally-run OpenSandbox server
A pure-stdlib hybrid Code-as-Action scientific research agent.
Prova Labs
Behavior attestation SDK for AI agents on Solana — wrap any agent action in a cryptographic receipt
SandboxAQ
Lightweight SDK for routing AI agent LLM traffic through the FlintAI guardrails proxy
Old Website Finder
Hermes-style CLI agent that finds outdated Uzbekistan websites and runs deep upgrade analysis (Grok/GPT/Claude/Gemini)
optimus - meta-skill for LLM/agent tooling (wiki, caveman, aura, graphify). Installs the prebuilt Rust binary as `optimus`.
...moreMicrosoft Corporation
SDK for building decentralized identity wallets and enterprise agents.
lynox-ai
Run your business, not your tools — AI runtime for CRM, workflows, research, monitoring. Self-hosted or managed hosting. Source-available (ELv2).
...morebadchars
90-tool MCP server for software supply chain security — OSV, GHSA, NVD, EPSS, CISA KEV, npm, PyPI, crates.io, RubyGems, NuGet, Packagist, Go, deps.dev, Scorecard, Rekor, ClearlyDefined, Repology, typosquatting detection
...morezquintero246
Sanctum — local-first agent orchestration engine. Cyclic state graphs, checkpointing, streaming, and robust tool-calling for local LLMs. Zero-dependency core.
...moreBennedictQuanTon
BKAi is an admissions counseling AI for Ho Chi Minh City University of Technology (HCMUT / ĐHQG-HCM). It layers a counselor policy (clarify → retrieve → advise) on top of an Agentic RAG backbone so answers stay grounded in official CSV/Markdown knowledge—not free-form LLM guesses—while supporting multi-turn chat, voice, and an owner evaluation loop
...morearec1b0
A DevOps/SRE runbook agent: it ingests Prometheus Alertmanager alerts, triages them with an LLM against a closed set of pre-approved runbooks, and executes remediation steps through a safety chain of input validation, human approval, and automatic rollback.
...moreAndrew Grigorev
PostgreSQL-backed task backend for coordinating multi-agent autonomous software development
ryanbaumann
Generate professional infographic PNGs from text with Gemini — a research agent (gemini-3.5-flash) prepares and validates the prompt, then gemini-3.1-flash-lite-image renders it. No browser/Playwright deps.
...moresdsrs
面向 Ubuntu 的安全检测/加固/防护 skill，供 Claude Code / Codex 等 AI agent 调用，支持 npm/npx。脚本只生成不执行，全流程脱敏。
GitHub Actions
Agent-friendly GitHub issue management layer for Pi using GitHub APIs and local issue files.
GitHub Actions
Unified LLM API with automatic model discovery and provider configuration
GitHub Actions
Gather a codebase (and its world) into one local knowledge store an AI agent answers from — deterministic, no LLM API, no DB.
...moreAman M
Predictive cost, policy, and runaway-session guardrails for AI coding agents
Arul Meiyappan Kannappan
Dual-agent AI coding system: Worker (llama3.1:8b) + Reviewer (devstral:latest)
SurrealDB
Spectron agent memory as tools for the Strands Agents SDK.
BRCOO
A visual, local-first desktop shell for Oh My Pi — sessions, tools, models, permissions, and long-running agent work.
bigsk1
Personal self-hosted AI assistant. Voice control, 80+ tools, and autonomous coding. Cloud providers or fully local with Ollama. UI, CLI, TUI. Deterministic (code-driven) orchestration!
...more