Autonomous AI agents that perform tasks independently
SkillSpector: Security scanner for AI agent skills (Claude Code, Cursor, and similar). Scans skills for vulnerabilities, malicious patterns, and security risks before installation. Supports Git repos, URLs, zips, and local directories; runs static pattern checks and optional LLM semantic analysis; outputs terminal, JSON, and Markdown reports with risk scoring.
...morePraveen <[email protected]>
Real-time memory health monitor and context rot detector for AI agents
Persistent agent runtime. Deploy agents that remember, survive crashes, and run forever.
rezabaram
Local coordination layer for AI agent teams: shared backlog, roles, reservations, review state, journal, and prompt context
...moresscodeai
日本の IT 開発、SIer、受託開発、自社サービス、SaaS、EC、製造業 DX 向け AI 専門家エージェント集
Cost control for AI agents — track per-user costs, enforce spending limits, and get real-time alerts. Auto-instruments OpenAI and Anthropic.
...moreRavindran M
AI Security for Multi-Agent LLM Pipelines
sancovp
Programmable, LEADER-DRIVEN agent teams on CAVE: a team leader (an intelligent dovetail) orchestrates teammates by writing message files, guard-railed by conditions on messages, on an ephemeral CAVE server. Compose teams with a tiny algebra; run ANY agent runtime (MiniMax/Claude shown). Requires the CAVE runtime.
...moreArchit Dwivedi
An OpenAI-compatible LLM router that saves cost without losing quality.
Provider-agnostic LangChain agent framework with middleware and evals.
mikhailsal
An experimental framework for autonomous, self-evolving AI agents living on a server with cross-session state and persistent memory.
...moreFMXExpress
Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.
...moregeniusdapeng-collab
Hollywood-grade AI video production system: Multi-Agent orchestration, 25-field cinematic shot language, and automated filmmaking pipeline. Built for AI agents.
...moreneural-agi
A local first, open source coding agent framework focused on building Codex like project assistance through a modular, testable, and extensible architecture.
...moreishandesigner77
Open-source agentic AI browser — browses, searches & automates the web for you. Parallel AI agents, BYOK (OpenRouter), 100% local. Electron + React.
...moreUtilities for LangChain
FORMAAI
FORMAAI — the AI Agent Firewall. Zero-config capture of every LLM call, human approvals, kill switch, and a cryptographically signed audit trail.
...moreCybWu
Surround any LLM with verifiable capability networks (exact math, knowledge, web) and say each result back in its own voice.
...moreimzx
High-performance AI Agent SDK — Rust core (NAPI-RS) + TypeScript orchestration
emadjumaah
Local vector / semantic search for @monlite/core, powered by sqlite-vec. Adds collection.findSimilar().
showang
領域無關的 agent 底座（kernel + 可插拔 DomainPack），從 xitto-code 抽象而來
dabitoo
Hashline edit support for Pi: the hledit hash-anchored file editing extension for AI coding agents.
Maximilian König
In-Context Reinforcement Learning framework for LLMs — no fine-tuning required.
autohandai
Autohand Code Agent SDK - CLI wrapper implementation