Search

Governed-knowledge retrieval + injection for LLM agents -- concepts, playbook entries, three-scope shadow merge, and before_model middleware

Tool framework for LLM agents -- routing, execution, and builtin tools

General purpose agent harness inspired by Claude Code

Split any text for LLM or RAG or Agent.Specially supports block-based splitting, keeping Markdown elements intact.

Unison (万物一心) — Loop Engineering pipeline for multi-agent collaboration

Cybara - Your agents. Your tools. Your runtime. Harness the power of AI

An AI strategy consultant (Claude Code agent) that interviews you instead of answering — structured, hypothesis-driven problem solving compiled into a working agent.

A hybrid AI assistant framework linking structural workflow engines and reasoning LLM agents through LangGraph-powered session control and task switching. 混合 AI 助手框架，通过 LangGraph 驱动的会话控制与任务切换，连接结构化工作流引擎与推理型大模型智能体。

A complete LLM agent in ~200 lines of C++ on an ESP32-S3

Find out whether your AI agent's evals are lying to you: stability reports with flip attribution, LLM judge audits, and deterministic checks mined from your KB.

Isnād–Rijāl framework for claim-level provenance in multi-agent knowledge systems

Harnessie: a brain-agnostic multi-agent harness (orchestrator / workers / verifiers) with verification gates, consent-based orchestration, ownership lanes, adversarial decision records, routing policy, and a tamper-evident audit log.

Export Claude Code token usage (per agent/model) to Prometheus, OTLP, or stdout -- parsed from transcripts, works on Max/Pro subscriptions.

Move and install AI agent skills between Claude, Codex, Cursor, and project scopes.

OpenAI Agents SDK sandbox provider backed by cocoon microVMs

Pure SDK kernel for long-lived nanobot operations agents

ORM + Access Control Layer for AI Agents

v0.6 signing-time gate for Solana: decode any base64 tx offline, classify 37 danger primitives + Native Stake + bounded ATA/Memo recognition + a 14-program DeFi/NFT clear-signing registry, resolve ALTs and clear-sign Squads proposals with --rpc, optionall

Autonomous DLMM LP agent for Meteora on Solana

KasbahOS — govern any AI agent in one line. Cryptographic receipts, multi-layer threat detection, drop-in middleware for OpenAI, Anthropic, LangChain.