What's Changed
- doc: changelog for 0.3.0 by @nicoloboschi in #156
- doc: update expired Slack invite link by @cdbartholomew in #157
- feat: add cloud mode to skill installer for team memory sharing by @cdbartholomew in #158
- Fix skill installer test examples to use meaningful content by @cdbartholomew in #160
- feat(cli): accept more file types on retain-files by @nicoloboschi in #163
- feat: introduce mental models by @nicoloboschi in #132
- doc: refinement for 0.3.0 new features by @nicoloboschi in #159
- Add structured JSON logging support by @cdbartholomew in #170
- feat: improve mental model refresh and add directives by @nicoloboschi in #166
- chore: unify agents.md and claude.md by @nicoloboschi in #173
- fix(sec): upgrade vulnerable deps by @nicoloboschi in #174
- feat(clients): mental models api by @nicoloboschi in #172
- fix: pytorch init failures by @nicoloboschi in #175
- feat: new 'worker' service by @nicoloboschi in #176
- chore: drop unused access_count column by @nicoloboschi in #178
- fix: improve pytorch model initialization to prevent meta tensor issues by @nicoloboschi in #180
- fix: sometimes memories gets extracted in the wrong language by @nicoloboschi in #184
- fix: simplify pytorch model initialization to prevent meta tensor issues by @nicoloboschi in #185
- feat: revisit mental models, directives and reflections by @nicoloboschi in #179
- Fix Gemini tool response format by including function name by @cdbartholomew in #187
- feat(python-sdk): add tags filtering support to high-level client by @phamgialinhlx in #186
- feat: support for npx add-skill by @nicoloboschi in #191
- feat(mcp): add timestamp to retain by @nicoloboschi in #190
- fix: improve mental model consolidation by @nicoloboschi in #197
- feat(litellm): async retain, reflect support, and API cleanup by @DK09876 in #167
- Fix: Pass api_key to Hindsight client in litellm integration by @cdbartholomew in #193
- chore: versioned docs by @nicoloboschi in #198
- doc: mental models by @nicoloboschi in #199
- ci: add upgrade tests by @nicoloboschi in #200
- fix(ui): reflections based on don't show up all contents by @nicoloboschi in #203
- feat(litellm): support tags and mission in litellm package by @nicoloboschi in #202
- chore: internal renames by @nicoloboschi in #204
- fix: include tags, created_at, proof_count in graph table_rows by @cdbartholomew in #207
- fix: multi-tenant schema context for worker task execution by @cdbartholomew in #208
- chore: drop dead code by @nicoloboschi in #210
- fix: misc fixes for observations and mental models by @nicoloboschi in #209
- chore: cleanup benchmarks runner with old flags by @nicoloboschi in #212
- feat: add custom extraction prompt by @nicoloboschi in #213
- fix: graph endpoint not showing links for observations by @nicoloboschi in #214
- fix(embed): daemon process XPC connection crash on macos by @nicoloboschi in #215
Full Changelog: v0.3.0...v0.4.0