#agent

Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.

Compact PHP repository symbol maps for coding-agent navigation.

Working-memory layer for coding agents: per-task session plans, decisions, assumptions, checkpoints, claim metadata, and retention.

Workflow orchestration for Pi

The core of FrontierHarness

Pi client/server fork for proxy-safe incremental requests

Vis is a coding agent that combines tools into Python programs. It can chain operations, run them in parallel, and inspect results before deciding what belongs in the conversation.

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.

Governed, durable-ready AI agent (chat + tool-calling + governance + HITL) for AdonisJS — part of the Agora ecosystem

The `npx serve` of Apple Simulators.

Google Workspace CLI for agents — designed with AXI (Agent eXperience Interface).

Self-hosted AI agent for automation, messaging, tools, integrations, and device control.

Local-first tool that autonomously turns GitHub issues into pull requests — backlog/queue board, CI babysitting, auto-merge, and cost tracking.

Multi-platform IM channel bridge with unified message abstraction for AI agents and bots

Lovable for your terminal: a frontend harness on top of Claude Code, Codex, and 6 other coding agents.

该仓库未发布描述。

Agent-agnostic automated development loop: Plan -> Build -> Test -> Review -> Verify -> Ship -> Learn -> Improve

cecli - a neat cli assistant

Utilities for LangChain

该仓库未发布描述。

Model-agnostic agentic runtime for the terminal — any local model becomes a capable agent. The intelligence lives in the harness, not the weights.

WebUI for PI

Synchronize, manage, and share your ai rules, skills, commands, subagents (Cursor, Claude Code, Copilot, OpenCode, Trae AI, Codex, Gemini CLI, Warp) with ease.

该仓库未发布描述。

Self-hosted agent for infrastructure

A simulated interaction and evaluation loop over oneharness: drive a harness through a multi-turn conversation and score the transcript.

One Works application monorepo for AI agents, plugins, desktop, web, CLI, and Relay.

A universal git-native AI agent framework. Your agent lives inside a git repo — identity, rules, memory, tools, and skills are all version-controlled files.

A highly extensible Markdown editor. Version control, AI Copilot, mind map, documents encryption, code snippet running, integrated terminal, chart embedding, HTML applets, Reveal.js, plug-in, and macro replacement.