v0.3.0

What's Changed

• feat: configurable embedding dimensions + OpenAI Embeddings by @nicoloboschi in #101
• fix: groq llm with free tier doesn't work by @nicoloboschi in #102
• Fix Python SDK not sending Authorization header by @cdbartholomew in #106
• Load .env file automatically on startup by @cdbartholomew in #104
• fix: make retain max completion tokens configurable by @nicoloboschi in #109
• fix: improve causal links detection by @nicoloboschi in #111
• ci: pin rust lock version by @nicoloboschi in #112
• feat: backup/restore by @nicoloboschi in #110
• fix(security): fix qs - CVE-2025-15284 by @nicoloboschi in #113
• feat: run db migrations offline (optionally) by @nicoloboschi in #114
• feat(helm): add existingSecret support by @nuclon in #119
• feat: Add per-request LLM token usage metrics by @omototo in #117
• feat(mcp): add async_processing parameter to retain tool by @slayoffer in #95
• fix: ui shows only 1000 memories by @nicoloboschi in #121
• feat: add metrics for llm call latency by @nicoloboschi in #120
• feat: support cohere as embeddings and reranker by @nicoloboschi in #122
• feat: support for multilingual content by @nicoloboschi in #124
• fix(mcp): add back bank list and create_bank tools by @nicoloboschi in #123
• feat: support different provider/models per operation by @nicoloboschi in #125
• fix: duplicated causal relationships and token optimization by @nicoloboschi in #126
• feat: add configs for database connection by @nicoloboschi in #128
• feat: delete memory bank by @dcbouius in #127
• feat: add operation_id to retain response by @nicoloboschi in #129
• chore: add flag to not include ml libs in docker image by @nicoloboschi in #130
• ci: fix flak tests by @nicoloboschi in #131
• Fix stats endpoint missing tenant authentication by @cdbartholomew in #134
• Fix embedding dimension for tenant schemas by @cdbartholomew in #135
• fix: misc perf improvements by @nicoloboschi in #133
• feat: retain modes by @nicoloboschi in #136
• fix: improve tei client parameters by @nicoloboschi in #137
• fix(typescript-client): Add error handling to all API methods by @nicoloboschi in #139
• misc: performance improvements by @nicoloboschi in #140
• ci: frozen uv sync by @nicoloboschi in #138
• fix: improve graph retrieval on large memory banks by @nicoloboschi in #141
• fix: entities list only show 100 entities by @nicoloboschi in #142
• fix: improve mpfp retrieval by @nicoloboschi in #146
• fix: batch queries on recall by @nicoloboschi in #149
• feat: support custom url for openai embeddings & cohere by @nicoloboschi in #150
• feat: add tenant to metrics labels by @nicoloboschi in #151
• feat: support litellm gateway by @nicoloboschi in #154
• Fix: Load extensions in server.py for multi-worker deployments by @cdbartholomew in #155
• feat: add memory tags by @nicoloboschi in #152

New Contributors

• @nuclon made their first contribution in #119
• @omototo made their first contribution in #117
• @slayoffer made their first contribution in #95

Full Changelog: v0.2.1...v0.3.0

v0.2.1

What's Changed

• doc: changelog for 0.2.0 (and regenerate clients) by @nicoloboschi in #99

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

v0.2.0

What's Changed

• doc: add skills documentation by @nicoloboschi in #73
• Load operation validator extension in main entry point by @cdbartholomew in #72
• feat(config): Add configurable observation thresholds by @bjornslib in #83
• fix(mcp): Chain MCP lifespan with FastAPI app lifespan by @bjornslib in #81
• feat: Add Anthropic Claude and LM Studio provider support by @csfet9 in #36
• feat(doc): add new config options and supported providers by @nicoloboschi in #84
• feat: add max_tokens and structured output to /reflect by @nicoloboschi in #74
• Add operation validator extension support with proper HTTP error handling by @cdbartholomew in #86
• Feature/graph viz by @chrislatimer in #85
• feat: Add local LLM improvements for reasoning models and Docker startup by @csfet9 in #88
• feat: Add user-provided entities support to retain endpoint by @phamgialinhlx in #91
• feat(mcp): Add multi-bank access and new MCP tools by @bjornslib in #82
• misc: add mcp integration tests and increase test coverage by @nicoloboschi in #98

New Contributors

• @bjornslib made their first contribution in #83
• @csfet9 made their first contribution in #36
• @phamgialinhlx made their first contribution in #91

Full Changelog: v0.1.16...v0.2.0

v0.1.16

Full Changelog: v0.1.15...v0.1.16

v0.1.15

What's Changed

• feat(misc): update clients types, test coverage, improve /health endpoint and add changelog by @nicoloboschi in #70
• feat: delete document from ui by @nicoloboschi in #71

Full Changelog: v0.1.14...v0.1.15

v0.1.14

What's Changed

• fix: embed get-skill installer by @nicoloboschi in #69

Full Changelog: v0.1.13...v0.1.14

v0.1.13

What's Changed

• fix: propagate exceptions from task handlers to enable retry logic by @cdbartholomew in #65
• feat: refactor hindsight-embed architecture by @nicoloboschi in #66
• fix(ui): timestamp is not considered in retain by @nicoloboschi in #68

Full Changelog: v0.1.12...v0.1.13

v0.1.12

What's Changed

• fix: set max_completion_tokens to 100 in llm validation by @nicoloboschi in #59
• ci: finalize test for the documentation code by @DK09876 in #57
• Improve LLM JSON parsing error handling with retry logic and detailed logging by @cesarandreslopez in #61
• feat: extensions + astral ty checks + docs improvements by @nicoloboschi in #54
• doc: add documentation for extensions by @nicoloboschi in #62
• fix: ollama structured support by @nicoloboschi in #63
• feat: add hindsight-embed and native agentic skill by @nicoloboschi in #64

New Contributors

• @cesarandreslopez made their first contribution in #61

Full Changelog: v0.1.11...v0.1.12

v0.1.11

Full Changelog: v0.1.10...v0.1.11

v0.1.10

Full Changelog: v0.1.9...v0.1.10