The Zeta Core is the project's permanent, structured, exportable knowledge.

SmartApp Brain recognizer for SaluteJS

Universal clan runtime for the Jungle — set up an AI agent for any project, anywhere. Persistent brain by default + one-shot `wild` install for standalone Claude Code integration.

Standalone Node MCP server: semantic search + knowledge graph + vault editing for Obsidian, no plugin required.

Shared hub modules of the AIOS workspace toolkit (AIO-601, multi-repo split): agent-runtime registry, workspace content parsers, brain/linear clients, git-backed file enumeration, and the engineering-constitution digest loader. ESM subpath exports only —

Claude subprocess LLM provider for brain-core

A markdown brain that gives your AI coding tools judgment and rigor: sharp defaults, real decisions, and the discipline to verify before saying done. For Claude Code, Cursor and Codex. Versioned, provenance-signed installer.

OpenAI text-embedding provider for brain-core (inference-plane EmbeddingProvider)

Connect MCP clients (Claude Desktop, Claude Code, Cursor) to a Third Brain server: device-code sign-in, one-command client install, and a stdio-to-HTTP MCP bridge. Zero dependencies.

Multi-harness dashboard for agents you own — Claude Code, Codex, Cursor, Antigravity, Hermes, and OpenClaw, with a permanent Brain of memory that survives any harness or model swap. Install with `npm install -g @agentis-labs/cli`.

Local-first memory and hybrid retrieval library for LLM agents with pluggable stores, BM25 plus vector search, and a four-stage memory pipeline.

Rigour sidecar inference binary package for linux-x64

GTM² in your terminal. Talk to your go-to-market system.

Shared markdown/HTML → print-ready document shell for brain-kit (used by the UI's /api/render and the CLI's `brain render`)

<!-- npm package README for the public ocean-brain CLI.

Shared memory, impact analysis, and guardrail hooks for AI coding agents — authored once, emitted as native config for Claude Code, Codex, Cursor, Gemini, Aider, and more.

A framework for reliable, thorough thought. Weave threads of thought via stitches.

AI agent orchestrator using the Octopus Model

Run your own agents as E2EE NoPeek bots. Pairs with one-time codes (multiple accounts per computer), runs every bot each account owns, and pipes messages to any command or webhook.

brain-kit module: job-search pipeline — board scraping, scoring, dedup, triage