DOCS
Every doc is a reference of something that already ships. Read in order for the full picture, or jump to what you need — historical decisions live in commits, planned work in the ROADMAP.
README.md
Start here. The public thesis: local-first, user-owned agent infrastructure.
read → 02 · guideINSTALL.md
Install methods (uv, pipx, dev), update path, uninstall, troubleshooting, supported platforms.
read → 03 · guideQUICKSTART.md
Install, pick a model, pin a workspace, send a first message, and check health.
read → 04 · guidePROFILES.md
The isolation primitive: identity, keys, memory, skills, peers, schedules, and cost.
read → 05 · guideSKILLS.md
Directory contract, frontmatter, scanner, validation, secrets, and bundled namespace.
read → 06 · guideMODELS.md
Model tiers for tool-heavy agent use: quality, cost/service, and local Ollama.
read → 07 · referenceALP.md
Alpi Link Protocol: pinned identity, signed envelopes, peer capabilities, workgroups.
read → 08 · referenceARCHITECTURE.md
Code structure, turn loop, memory, sessions, email tool, scheduler, MCP, logging.
read → 09 · referenceCONFIG.md
Every YAML knob, its default, what it controls.
read → 10 · referenceSECURITY.md
Two-layer security model. Approval system, SSRF, prompt-injection, sensitive paths. Sandbox.
read → 11 · opsDEPLOYMENTS.md
launchd on macOS, systemd on Linux. Per-machine daemon, scheduler, keep-alive, logs.
read → 12 · opsOPERATIONS.md
Day-2 runbook. Doctor, diagnostics, log rotation, backup, recovery, upgrade.
read → 13 · referenceINTEGRATIONS.md
Talk to a profile or workgroup from your own code: a scoped device token over the host-plane WebSocket, host.chat.send frames, workgroup methods, and a Node example.
read → 14 · legalLICENSE.md
Legal terms for the source-available agent core and Apache-2.0 Alpi Link Protocol.
read → 15 · planningROADMAP.md
Open release gates, ALP launch work, long-term bets, and discarded decisions.
read → 16 · logCHANGELOG.md
Version-by-version log of user-visible changes since v0.1.
read →