v0.0.10 is where liminal-ai main sits today: MIT-licensed, still alpha. Task Worlds landed earlier on May 23 then was ripped out the same day in favor of tighter execution state and compensation wiring.

v0.0.10
Changelog milestone (alpha)
Alpha
Release stage today
22
Eval scenario packs
2
UIs (TUI + Web)

Shipped in this slice

  • liminal CLI (dev) — setup, doctor, web, tui, update, path
  • Install scripts: scripts/install.sh, scripts/install.ps1 (alpha onboarding — not a GA release)
  • Recipe library v2 — compounds on strategy shape, not generic “recipe:” notes
  • Harness power pass — execution state, compensation playback, breakdown, tool DAG depends_on, contract→tool mapping
  • Workflow evals + additional core baseline tests
  • Web fetch — Wikipedia extracts, pagination, distill bypass, model max_chars floor
  • Persona UI themes — distinct deterministic palettes, hue-preserving normalization, HudShell theme wiring
  • Closed-loop tuning hooks, per-harness workspace root, streaming edit previews in web
  • OpenRouter attribution unified across sidecar calls

Removed (same day)

What you can run today

Clone the repo, set AGENT_API_KEY in .env, build core + tools, then:

npm run tui
# or
npm run web

Optional: run the install script or liminal setup after building.

Alpha capability map (cumulative)

AreaStatus on main
HarnessReAct loop, retries, circuit breaker, compression, approvals, optional self-heal lint
WritesStreaming large-file writes + integrity checks
ToolsFiles, shell, git, code intel, web, browser + CAPTCHA, memory, vault, documents, orchestration, dynamic tools, MCP
ReasoningIntent routing, two-tier models, external think / reason, effort learning
PersonaBootstrap, generated themes, four web shells
Mission stateExecution state + epistemic subgoals (not Task Worlds)
ObservabilityJSONL traces, self_telemetry, recipe stats
Eval22 packs → .agent_eval_runs/ sink

Roadmap (not shipped)

StageMeaningStatus
v0.0.x alphaRapid iteration on mainYou are here (v0.0.10)
BetaAPI/default stability pass, broader dogfoodingNot started
RCRelease checklist, docs freeze candidateNot started
v0.1.0Public preview tag + npm/install GA storyNot started

Pre-release history

VersionDateSummary
v0.0.12026-05-03Monorepo + first loop
v0.0.22026-05-03Persona generation
v0.0.32026-05-05Lazy tools + hybrid recall
v0.0.42026-05-08Vision, markets, doc engine
v0.0.52026-05-09Upgrade V / DAG
v0.0.62026-05-10MCP + research tiers
v0.0.72026-05-12JSONL + world context
v0.0.82026-05-15Settings + persona UX
v0.0.92026-05-22Browser + reasoning + writes
v0.0.102026-05-23Execution state pass + dev CLI (current)

Still out of scope for alpha

  • Hosted team plane or cloud sessions
  • VS Code / JetBrains extensions
  • npm global package publish
  • Official Docker image
  • Task Worlds (removed; no current replacement product surface)

Try the alpha on your machine

Clone from GitHub. MIT licensed. Node 22+ and your own API key. Beta and public preview coming later.