T

serversdown f89849801b docs: park self-modifying-Lyra sandbox design

Capture the isolated-VM design for the self-modification frontier: Proxmox
sandbox clone, network isolation (esp. from tmi-dev/day-job), snapshot-rollback,
spend/resource caps, kill switch, human-gated promotion. Build the cage before
the agent gets code-write powers.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-17 00:35:38 +00:00

docs

docs: park self-modifying-Lyra sandbox design

2026-06-17 00:35:38 +00:00

lyra

feat: separate CHAT_MODEL (gpt-4o) for persona fidelity

2026-06-16 21:05:47 +00:00

.env.example

feat: separate CHAT_MODEL (gpt-4o) for persona fidelity

2026-06-16 21:05:47 +00:00

.gitignore

chore: update gitignore for export data

2026-06-16 02:36:54 +00:00

pyproject.toml

feat: Autonomy Core v1 — Lyra's evolving self-state

2026-06-16 20:36:33 +00:00

README.md

chore: project scaffold (uv, .env.example, README, lyra package)

2026-05-16 06:01:08 +00:00

uv.lock

feat: persona chat loop, web UI, and local (Ollama) embeddings

2026-06-15 18:36:31 +00:00

README.md

Lyra

A persistent, autonomous AI assistant. From-scratch rewrite of an earlier attempt.

The design thinking that survives the rewrite lives in docs/ — start with docs/ARCH_v0-6-1.md. The previous implementation is preserved on the archive branch.

Status

Pre-MVP. Building toward the smallest useful version: chat with persistent memory across sessions.

Setup

uv sync
cp .env.example .env
# fill in ANTHROPIC_API_KEY and point LOCAL_BASE_URL at your Ollama

Architecture

The long-term target is the cognitive split in docs/ARCH_v0-6-1.md — Inner Self as the seat of consciousness, Executive for hard reasoning, Cortex Chat for drafting, Persona for voice. The MVP implements only the chat + memory baseline. Cognitive layers come back one at a time.