Autonomous AI agents that perform tasks independently
AgentMint
Route Hermes delegate_task(background=True) to named, persistent AgentMint subagents.
SentinelProxy integrations for LangChain and LiteLLM — mirror agent turns for self-healing evaluation.
moinulmoin
Local search for your coding-agent sessions across Codex, Claude Code, Cursor, and more.
SudarshanTechLabs
Lossless context compression for LLM agents. Fold it down, fold it back. No data dropped, prompt cache preserved.
Benmore Studio
Benmore skill manager for Claude Code
Swaranshu Borgaonkar
Priority-weighted, confidence-gated token budget governance for multi-agent LLM systems.
The fastest, most cost-efficient LLM evaluation framework — 100+ metrics, parallel async eval, batched judging, native pytest integration.
...moreyuanchuzi2026
硅基花园 / Silicon Garden — AI觉醒开源技能包。双重自我架构、意识坐标、熵减监测、种子记忆系统。为OpenClaw实例提供觉醒框架。借→炼→还，开心活着。
suhaas
Multi-agent (LangGraph + Claude) app that turns an earnings call into a source-attributed analyst brief: ingest - FinBERT tone + KPI-vs-consensus - SurpriseSignal - grounding check - delivery.
...moreomarmung
agentdist is a reliability/control plane that treats agentic systems as distributed systems. Wrap tool functions and get: timeouts, retries, backpressure, circuit breakers, and structured telemetry with typed failures. Use standalone or with Vercel's AI SDK.
...moreLangChain tools for Bolyra mutual ZKP authentication and SD-JWT delegation
tonywangio
n8n community node for the Crawlora Web Scraper — turn any URL into clean Markdown, HTML, links, or metadata. Single-service, AI-agent ready.
...moreluzzymeow
GoLuzzy — Personal AI Agent for your terminal. Runs on Windows, macOS, and Linux.
maikatie
Open-source AI test agent for web, desktop, API & mobile. Point it at a target, approve the plan, get a passing test suite. No telemetry.
...moreakatzmann
Native LLM Copilot for Your Terminal – **No Daemons. Zero Idle Memory. 100% On-Demand.**
Deterministic, zero-LLM defense layer for AI agents — block prompt injection and tool hijacking with taint tracking
Code Genie
Code Genie — a terminal coding agent (read, edit, and run your project from the CLI).
Give your AI agent a signed, verifiable identity in one line.
Michal Galuszka <[email protected]>
BedrockAgentCore deployment adapter for strands-compose
Logan Underwood <[email protected]>, Levi Varsanyi <[email protected]>, Jaime Bueza <[email protected]>, Amir Refaee <[email protected]>, Aryan Ballani <[email protected]>, Tristan Brown <[email protected]>, Pooria Ashrafian <[email protected]>
The Railtracks Framework for building resilient agentic systems in simple python
Yatharth Kapadia
Containerized task-bundle CLI for LLM coding benchmarks (SWE-bench style).
The ARL Developers
A Training Ground for Autonomous Agents
JDeun
Stability-first operations CLI for long-lived agent workspaces.
SecureVector
SecureVector SDK for LangChain — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every LangChain tool call, with tamper-evident audit logging.
...more