v0.2.9

What's Changed

• refactor: SQLite-first cutover for all local read paths by @WellDunDun in #66

Full Changelog: v0.2.8...v0.2.9

v0.2.8

What's Changed

• fix: restore main deploy workflows after auto-bump by @WellDunDun in #63
• refactor: dashboard routes, SQLite-first architecture, auto-update by @WellDunDun in #64
• feat: alpha upload V2 pipeline with hardened telemetry contract by @WellDunDun in #65

Full Changelog: v0.2.6...v0.2.8

v0.2.6

What's Changed

• fix: resolve workspace:* protocol to enable npm install by @WellDunDun in #62

Full Changelog: v0.2.5...v0.2.6

v0.2.5

What's Changed

• feat: anonymous usage analytics + fix all code scanning alerts by @WellDunDun in #59
• feat: version update check in selftune doctor by @WellDunDun in #60
• feat: extract @selftune/ui shared component package by @WellDunDun in #61

Full Changelog: v0.2.2...v0.2.5

v0.2.2

What's Changed

• v0.2.1 release by @WellDunDun in #53
• chore: update workflows and config from master/dev to main by @WellDunDun in #57
• chore: bump version to v0.2.2 by @WellDunDun in #58

Full Changelog: v0.2.1...v0.2.2

v0.2.1

What's Changed

• Add workflow discovery and CLI command (v0.3) by @WellDunDun in #30
• Fix all 13 demo findings by @WellDunDun in #29
• docs: Align selftune skill docs with shipped workflows by @WellDunDun in #31
• Fix BUG-7, BUG-8, BUG-9 from demo findings by @WellDunDun in #32
• Fix dashboard data and extract telemetry contract by @WellDunDun in #33
• Fix telemetry normalization edge cases by @WellDunDun in #34
• Update package metadata for selftune-dev by @WellDunDun in #35
• Prepare 0.2.1 release by @WellDunDun in #36
• feat: harden LLM calls and fix test failures by @WellDunDun in #38
• Add local SQLite materialization layer for dashboard by @WellDunDun in #42
• feat: implement autonomous selftune orchestrator core loop by @WellDunDun in #40
• Build(deps): Bump oven-sh/setup-bun from 2.1.2 to 2.1.3 by @dependabot[bot] in #26
• Build(deps): Bump actions/setup-node from 6.2.0 to 6.3.0 by @dependabot[bot] in #27
• Build(deps): Bump github/codeql-action from 4.32.4 to 4.32.6 by @dependabot[bot] in #28
• Improve sync progress and tighten query filtering by @WellDunDun in #43
• feat: generic scheduling and reposition OpenClaw cron as optional by @WellDunDun in #41
• feat: add local dashboard SPA with React + Vite by @WellDunDun in #39
• Prepare SPA dashboard release path by @WellDunDun in #44
• feat: phased decision report for orchestrator explainability by @WellDunDun in #48
• feat: evidence-based candidate selection gating by @WellDunDun in #50
• E2E autonomy proof harness for evolution pipeline by @WellDunDun in #51
• feat: persist orchestrate run reports in dashboard by @WellDunDun in #49
• feat: demo-ready CLI consolidation + autonomous orchestration by @WellDunDun in #52

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• Add FOSS playbook: license, CI, community docs, badges by @WellDunDun in #3
• Add CLI status commands: dashboard, last, status by @WellDunDun in #4
• Sync dev with master, remove duplicate README badges by @WellDunDun in #14
• Add replay and contribute: retroactive backfill and community contribution export (v0.7) by @WellDunDun in #13
• Add PAI Infrastructure patterns to selftune by @WellDunDun in #15
• feat: sandbox test harness, multi-agent expansion plan, and project roadmap by @WellDunDun in #17
• feat: Add cron jobs, OpenClaw ingestor, and sandbox testing by @WellDunDun in #16
• Audit skills vs PRs, add workflows, polish README by @WellDunDun in #19
• feat: Add 4 eval improvements — pre-gates, graduated scoring, failure feedback, Pareto by @WellDunDun in #18
• feat: Expand selftune from description-only to full skill evolution by @WellDunDun in #20
• Add badge branding, exec-plans, and Conductor setup script by @WellDunDun in #21
• Align README with selftune.dev branding and v0.2.0 by @WellDunDun in #22
• Implement dashboard audit: 4-state status, eval feed, search, data contract by @WellDunDun in #23
• Reframe messaging to self-improving skills, consolidate v0.2.0 by @WellDunDun in #24
• Release v0.2.0: self-improving skills by @WellDunDun in #25

Full Changelog: v0.1.4...v0.2.0

v0.1.4

What's Changed

• Bump @biomejs/biome from 1.9.4 to 2.4.4 by @dependabot[bot] in #9
• fix: audit release gaps, fix publish workflow, address CodeRabbit review by @WellDunDun in #12

Full Changelog: v0.1.2...v0.1.4

v0.1.2

What's Changed

• Release: CI/CD, FOSS playbook, CLI status commands by @WellDunDun in #6
• Bump ossf/scorecard-action from 2.4.0 to 2.4.3 by @dependabot[bot] in #8
• Bump actions/checkout from 4 to 6 by @dependabot[bot] in #11
• Bump actions/setup-node from 4 to 6 by @dependabot[bot] in #7
• Bump github/codeql-action from 3 to 4 by @dependabot[bot] in #10

New Contributors

• @dependabot[bot] made their first contribution in #8

Full Changelog: v0.1.0...v0.1.2

v0.1.0

Initial release of selftune — skill observability and continuous improvement CLI.

What's Included

• Session telemetry — Hooks for Claude Code and OpenCode, wrapper/ingestor for Codex
• False negative detection — Surfaces queries where a skill should have fired but didn't
• Eval set generation — Converts hook logs into trigger eval sets with real usage as ground truth
• Session grading — 3-tier evaluation (Trigger / Process / Quality)
• Skill evolution — Propose, validate, and deploy improved skill descriptions
• Post-deploy monitoring — Watch for regressions, auto-rollback on pass rate drops
• init command — Auto-detect agent environment, bootstrap config

Install

npm install -g selftune
selftune init

Zero runtime dependencies. Works with Claude Code, Codex, and OpenCode.