#ai-agents

Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero dependencies.

Markdown filesystem for agents and teams.

Local-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health｜本地优先 Rust TUI/CLI，审计 AI 编程 Agent 会话的成本、Token、延迟、失败与健康度

Universal memory runtime for AI agents

A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MCPs, Subagents, Agent Skills, controllable tool output retention, hashline edits, and more.

Lightweight AI agent library. Turn Python functions/classes into AI tools instantly. No verbose configs or complex abstractions.

The open MCP config tool - npx add-mcp

An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.

World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588

Agentic coding TypeScript boilerplate for Claude Code: sub-agent workflows with built-in quality checks and context engineering.

Extensions for Microsoft Agent Framework

CLI tool for running coding agents inside hardware-isolated microVMs

Spine — governed, provenance-grounded autonomous software delivery (installs as agent-orchestrator).

Aiden — Autonomous AI agent that operates your computer with prompts: browser control, terminal execution, workflows, tools, recovery systems, and persistent memory. Built solo. AGPL-3.0.

Simple, performant, battle-tested framework for building reliable AI applications.

A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT

Frontier AI video generation for coding agents - Seedance, Runway, Veo, Kling on your own keys, behind a hard cost cap. CLI + MCP.

Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon

Portable open-source starter kit for AI-assisted QA workflows. Copy .qa-ai/ into any QA or automation repo, bootstrap agent commands, and guide Claude Code, OpenCode, Codex and other tools from PRD/requirements to Gherkin tests, TestRail planning, traceability, automation feasibility and PR-ready QA artifacts.

Turn your company's scattered knowledge into AI ready Books ✨

Open-source, local-first personal AI assistant that lives on your computer, gets to know you over time, and keeps what matters moving.

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done.

One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.

Documentation-discovery telemetry for Claude Code — heat/cold maps, health grade, evidence-backed router fixes. 100% local, zero tokens. /tt

ThumbGate Pre-Action Checks derive rules from repeated failures, flag risky tool calls, hard-block detected secret leaks, and block matches in strict mode.

Agentic coding in your terminal,Simultaneously compatible with OpenAI, Gemini, and Claude.运行在终端的 AI 编程智能体，同时兼容 Deepseek、OpenAI、Gemini和Claude。

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.

The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs.

Terminal-first relay for paired AI coding agents (Claude + Codex), driven by structured workflows.