Skip to content

Releases: samrusani/AliceBot

Alice v0.5.1: Provider Adapters + Design Partner Launch

16 Apr 17:16

Choose a tag to compare

Alice v0.5.1 is the Phase 14 platform release for Alice.

This release makes Alice easier to plug into local, self-hosted, enterprise-curious, and external-agent workflows without changing its core continuity semantics.

Highlights

  • Provider/runtime portability across OpenAI-compatible endpoints, Ollama, llama.cpp, vLLM, and Azure-backed paths.
  • First-party model packs for llama, qwen, gemma, and gpt-oss with provider-aware bindings and pack-aware defaults.
  • Reference integration paths for Hermes, OpenClaw, and generic Python and TypeScript agents.
  • Design-partner onboarding, workspace linkage, usage summaries, feedback intake, and launch evidence.
  • Logging-safety hardening from HF-001: stdout-by-default local/Lite logging, disabled local/Lite access logs by default, and bounded opt-in file logging.

What shipped in this boundary

  • P14-S1: Provider abstraction cleanup + OpenAI-compatible adapter
  • P14-S2: Ollama + llama.cpp + vLLM adapters
  • P14-S3: Model packs
  • P14-S4: Reference integrations
  • P14-S5: Design partner launch
  • HF-001: Logging safety and disk guardrails

Release posture

  • Pre-1.0 public release
  • Version boundary: v0.5.1
  • Main focus: platform compatibility, adoption, and operational safety

For release verification and operational details, see the repo changelog and release docs in docs/release/.

v0.4.0

15 Apr 21:19

Choose a tag to compare

Alice v0.4.0 makes the system easier to adopt without changing its core continuity model.

This release adds a single continuity entrypoint for external agents, a lighter local startup path, and clearer visibility into memory quality and conversation health.

What is included

  • One-call continuity across API, CLI, and MCP
  • Alice Lite for a faster local first run
  • Memory hygiene visibility for duplicates, stale facts, contradictions, weak trust, and review pressure
  • Conversation health visibility for recent, stale, and risky threads

Why this matters

  • External agents can integrate through one main continuity call instead of stitching together multiple surfaces
  • Solo users and builders can get Alice running locally with less setup friction
  • Operators can see quality and risk posture more clearly without weakening Alice's continuity semantics

Baseline included in this release

  • Phase 12 retrieval, mutation, trust calibration, eval, and briefing stack
  • Hermes bridge support
  • Provider runtime and model-pack support

Verification

  • 1279 Python tests passed
  • 200 web tests passed
  • Alice Lite smoke passed
  • Hermes provider, MCP, and bridge demo smoke passed
  • Public eval harness passed 12/12 cases

Release boundary
This is the public pre-1.0 release for the completed Phase 13 surface.

v0.3.2

15 Apr 10:20

Choose a tag to compare

Alice v0.3.2 ships the completed Phase 12 boundary. This release adds hybrid retrieval and reranking, explicit memory mutation operations, contradiction detection and trust calibration, a public eval harness with checked-in baseline reporting, and task-adaptive briefing for user recall, resume, worker subtask, and agent handoff. It also includes the release-readiness pass and Phase 12 closeout documentation for the pre-1.0 public boundary.

Alice v0.2.0

14 Apr 11:02
988761c

Choose a tag to compare

Alice v0.2.0 is the next public pre-1.0 release of Alice, covering the shipped platform through Phase 11 and Bridge B1-B4.

What ships in this release:

  • Alice continuity core: typed memory, provenance, correction-aware recall, open loops, recall/resume/explain flows
  • CLI and MCP surfaces
  • Hosted/product layer shipped in Phase 10
  • Phase 11 provider runtime: workspace-scoped provider registration, adapters, and model packs
  • Hermes bridge: lifecycle hooks, prefetch, auto-capture, review queue, explainability, operator docs, smoke validation, and one-command demo path

Verification evidence:

  • control-doc truth: PASS
  • Python tests: 1191 passed
  • web tests: 199 passed
  • Hermes memory provider smoke: PASS
  • Hermes MCP smoke: PASS
  • Hermes bridge demo: PASS

Release notes:

  • recommended deployment path: provider_plus_mcp
  • fallback path: mcp_only
  • this remains a pre-1.0 release and is not a 1.0 compatibility or support guarantee