Search

Memoria persistente local-first para agentes AI — SQLite + FTS5 + HRR + embeddings opcionales

Command-line installer and launcher for Inferay.

Lightweight multi-agent chat server

Postgres + pgvector memory provider plugin for hermes-agent. Multi-agent storage layer with per-minion themes, async writer, no LLM in the memory hot path.

Lightweight chat relay for CLI coding agents

Local-first AI agent platform — self-host on Mac, PC, Linux, VPS, or NAS.

Bavimail Toolkit — first-party LangChain, CrewAI, LlamaIndex, and AutoGen integrations for the Bavimail email API

DeepSeek-V4-Pro - AI model available on ModelScope inference platform

A lightweight, general harness for tool-using LLM agents.

Local-first LLM agent observability — decorator + OpenTelemetry ingestion, traces grouped by execution pattern, cost per call, search, replay, shareable HTML snapshots.

SQLAlchemy dialect for chDB — the in-process SQL OLAP engine powered by ClickHouse. Unlocks LangChain SQLDatabaseToolkit, CrewAI NL2SQLTool, pandas.read_sql, Apache Superset, and Django ORM.

Python SDK for Pugmark — the durable agent runtime built on object storage

A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL.｜从零开始学 AI Agent 开发 | 系统、全面、实战导向的 Agent 开发教程 | 每日自动追踪 arXiv 最新论文 | Learn AI Agent Development from Scratch

一款企业级多语言(Polyglot)智能出行 Agent 架构实战。采用 Monorepo 单仓管理，底层基于 Java Spring Cloud 构建高并发票务微服务底座；AI 大脑层提供 Java (Spring AI) 与 Python (FastAPI+LangChain) 双引擎实现。核心特性包含：端到端 JWT 上下文鉴权透传、基于 Tool Calling 的异常自纠错 (Self-Correction) 循环，以及微服务级的数据流压缩，完整打通自然语言到真实复杂业务下单的全链路闭环。

AI-powered IT helpdesk assistant built with FastAPI, LLaMA 3.1, and agentic tool-use.

🌐 Build high-performance web sensing and browser automation tools with ReasonKit Web, a Rust-native implementation for efficient solutions.

Mentalist: (DeepAgent in rust) High-performance Rust agentic middleware & execution environment for autonomous AI agents. Implements DeepAgent methodology with execution hooks, explicit planning, sandboxed tool execution, and full session serialization. Built for production-ready agent systems.

A local-first, cost-conscious multi-agent workspace. Mission-first IA, dual-tier sandbox (shared + per-agent), audited self-evolution.

Runtime safety layer for autonomous AI agents. Policy enforcement, progress tracking, state revalidation, and behavioral baseline learning. Rust core with Python & Node.js SDKs.

macOS APFS transparent compression for cold agentic-CLI session JSONLs (Claude Code, Codex, Gemini).