Autonomous AI agents that perform tasks independently
GitHub Actions
Production-grade SEO, AEO, and GEO agent skill with auditable detection, claim governance, evidence validation, and multi-agent installation.
...moreatharvmunde11
Wolbarg — modular, provider-agnostic semantic memory SDK for AI agents. SQLite + PostgreSQL, optional graph memory (SQLite / Neo4j), hybrid search, ingest, and rerankers.
...morerudrendu_paul_packages
Local-only CLI that mines git history for file-level co-change patterns and builds a queryable knowledge graph for AI coding agents, with optional enrichment from graphify's symbol/call-graph output when it is installed.
...morecovyne
Cross-IDE agent framework for Unity/C# game-development — one-command install
oxbytebard404
.gitignore for AI coding agents — declare files your AI agent must not read.
youagentfactory
Raw JSON and YAML contract artifacts for you-agent-factory consumers.
Custos
Detect wasteful cycles in multi-agent traces (Custos / Clew, S0 MVP).
super-rick
AI MCN 自动推广工具 — 多Agent内容营销自动化，支持掘金/知乎/Dev.to
nerisma
Specialized agent system for pi: task delegation, activation/deactivation, and system prompt injection via .md files.
CocoRoF
Synapse — a learnable, lightweight graph-traversal memory engine: BM25 + local static embeddings + typed-edge PageRank + an online-learned ranker, in one SQLite file with zero API calls.
...moreMark Norman <[email protected]>
Typed framework for declaring and running agentic systems
seehiong
Automate Blender 3D modeling with AI via MCP — 93 tools for modeling, sculpting, architecture/MEP, materials, and 3D-print prep. Includes Blender Studio: a visual record/replay session editor with a multi-provider AI assistant (Claude, Gemini, OpenRouter) — drive it from n8n, Claude Code, or standalone.
...moreLangChain integration for qarai-agent-guard that provides runtime security for AI agents through threat detection, policy enforcement, and content protection.
...moreLogosAI Team
Knowledge-driven multi-agent orchestration with LLM-powered query analysis and intelligent agent selection
adourish
Agentic coding terminal for the shell (runPixel gateway / OpenAI-compatible / offline backends)
deskd contributors
A domain-agnostic orchestration engine for multi-agent desks: presence, a unified inbox, bounded meetings, and a wake ladder that proves delivery.
...moreGuardrails for AI-agent tool/function calls: schema validation, realistic error recovery, cost/quota budgets, circuit breakers, and response caching. Framework-agnostic.
...moreSelim Efe Lüleci
Local security/audit layer for Claude Code: logs every tool call, blocks sensitive file access, generates session reports.
...moreDachary Carey
Parses agent harness session logs into a unified event schema. Under development.
Mahesh Buddolu
ArchWright — the architecture auditor for AI agents
Framework-agnostic evaluation, observability, and reliability for LLM agents.
Aayush-Joshi-01
Async multi-agent AI library for Python — self-improving agent loops, APEX synthesis, bounded agent spawning, multimodal input, and true token streaming across 100+ LLM providers.
...morezerovia
Automate aim and item sales in Be A Lucky Block with this lightweight script.
hhyqhh
An open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab — built on the Pi SDK.
...more