Search

Detect stale facts in LLM agent memory stores

Dong AI Company — 多智能体 AI 公司框架

Fit your whole repo into any small model's token window — context selection for free/small LLMs.

Islo (islo.dev) sandbox integration for Deep Agents

Fragmented memory system for Hermes Agent — automatically retrieve relevant memory fragments and inject them into conversation context

Halo host adapter for the OpenAI Agents SDK (Python): a call_model_input_filter that swaps large tool results for a shape map (out of context) plus a halo_fetch navigation tool. install_halo() wires it in one call.

Run Claude Code agents in isolated, disposable sandboxes — one per task, with cheap rollback and a human gate.

Slim SDK for driving a deployed Ezra multi-agent platform over HTTP

A production-grade AI agent framework with 21 integrated tool classes and a four-role autonomous LLM pipeline — built on the NPMAI ECOSYSTEM.

Sift — deterministic website indexing for grep-first LLM agents

AI model: ekozzer/Qwen3.5-27B-W4A16-AWQ-Hybrid-Agent

AI model: mradermacher/MiniAGI-Agentic-beta-GGUF

AI model: kosiasuzu/agenticml-agent-llama-3.1-8b-init

MCP vision server for AI agents, Claude, Cursor, OpenCode, VS Code, local LLMs, Ollama, LM Studio, OpenRouter, Gemini, image analysis, and video understanding.

An AgentSkill for Java enterprise backend work — guides coding agents to investigate the repository first, then plan, implement, and verify changes. Framework-agnostic, MIT.

ZWISERFIT AI Store Manager — Hermes/OpenClaw agent system running gym operations 24/7. PoPB data pipeline + RWA tooling.

14 skills that write every document your open-source project needs — README to GOVERNANCE, professionally and consistently.

ZiroAgent SDK — production-safe TypeScript agent runtime: durable execution, cost guardrails, replayable traces, MCP-native, sovereign-ready. https://ziroagent.com

Persistent multi-agent Claude Code system with auto-restart, inter-agent task routing, structured memory, and Telegram control. Better than ClaudeClaw for autonomous AI agent teams. Free, open source.

A proof of concept for a mini harness containing a self-reflecting agent: an AI agent that audits its own traces, maintains an explicit self-model, and uses feedback to improve its behavior over time.