What's Changed
- blog: What's New in Hindsight 0.4.22 by @nicoloboschi in #818
- Fix timeline group sort: localeCompare → numeric Date comparison by @ThePlenkov in #820
- fix(deps): address critical and high severity security vulnerabilities by @dcbouius in #827
- feat(control-plane): add Constellation view with Pretext canvas rendering by @nicoloboschi in #831
- fix(db): respect vector extension config in per-bank index migration by @nicoloboschi in #832
- breaking-change: remove BFS and MPFP graph retrieval strategies by @nicoloboschi in #767
- fix(consolidation): improve observation quality with structured processing rules by @nicoloboschi in #814
- perf: 3-phase retain pipeline — fix deadlocks, cap temporal links, query-time entity expansion by @nicoloboschi in #722
- Add OpenClaw shared memory team setup guide by @benfrank241 in #788
- fix: resolve remaining Dependabot security alerts by @dcbouius in #833
- feat: add AutoGen integration for Hindsight by @DK09876 in #719
- fix: resolve 25 test regressions from streaming retain pipeline by @nicoloboschi in #836
- feat(openclaw): JSONL-backed retain queue for external API resilience by @akhater in #740
- fix(api): clear memories no longer deletes the bank by @nicoloboschi in #837
- fix(embed): clear stale daemon on port before starting (#843) by @nicoloboschi in #845
- feat: add detail parameter to list/get mental models by @nicoloboschi in #846
- fix(retain): preserve normalized experience fact types by @nicoloboschi in #848
- feat(api): bank template import/export by @nicoloboschi in #819
- feat(paperclip): add hindsight-paperclip TypeScript integration by @benfrank241 in #773
- Blog: Hindsight Is #1 on BEAM — the Benchmark That Tests Memory at 10M Tokens by @benfrank241 in #851
- fix(ci): resolve all CI failures by @nicoloboschi in #847
- docs(hermes): update integration docs for plugin overhaul (hermes-agent#5094) by @benfrank241 in #881
- blog: Hindsight is now a native memory provider in Hermes Agent by @benfrank241 in #882
- blog: Persistent Memory for AutoGen Agents with Hindsight by @benfrank241 in #883
- fix: use max_tokens for openai provider with custom base URL (Mistral compatibility) by @octo-patch in #858
- feat(helm): add persistent volume for local model cache by @isac322 in #861
- feat(google): add support for google embeddings and reranker by @ParadiseN1 in #863
- fix: Windows compatibility for hindsight-embed by @beordie in #867
- Fix AttributeError when event_date is None in fact_extraction by @Spectorisimo in #875
- chore(deps): bump actions/github-script from 7 to 8 by @dependabot[bot] in #879
- fix(query_analyzer): handle dateparser internal crashes gracefully by @cdbartholomew in #893
- fix(embed): skip profile .env overwrite when config has no HINDSIGHT_API_* keys by @octo-patch in #896
- fix(paperclip): address post-merge review fixes by @nicoloboschi in #900
- feat(recall): add proof_count boost to combined scoring by @Abdulkadirklc in #821
- fix(mcp): auto-coerce string-encoded JSON in tool arguments by @nicoloboschi in #899
- fix: make bank_id metric label opt-in to prevent OTel memory leak by @nicoloboschi in #898
- test: add regression tests for #874 and #894 by @nicoloboschi in #901
- feat: add OpenCode persistent memory plugin by @DK09876 in #853
- fix: add paperclip and opencode to changelog generator by @nicoloboschi in #903
- docs: add best practice for filtering recall by memory shape by @nicoloboschi in #905
- fix(config): validate entity_labels structure on PATCH by @nicoloboschi in #902
- fix(mcp): validate UUID inputs and add sync_retain tool by @nicoloboschi in #906
- security: bump litellm to >=1.83.0 (critical CVE fix) by @dcbouius in #912
- feat(openclaw): support bankId for static banks by @Aldoustheorchestrator in #910
- blog: One Memory for Every AI Tool I Use by @benfrank241 in #914
- fix(recall): cap entity fanout in graph expansion by @nicoloboschi in #911
- fix: remove hindsight-cloud tag from guest post by @benfrank241 in #916
- fix: update author name to Michael Bourkas by @benfrank241 in #917
- fix: clamp out-of-range content_index in _map_results_to_contents by @mango766 in #908
- security: bump vite across integrations (high CVE fix) by @dcbouius in #913
- security: bump lodash, lodash-es, defu in root lockfile by @dcbouius in #915
- fix: make LiteLLM SDK embeddings encoding_format configurable by @nicoloboschi in #928
- feat: include occurred_end and mentioned_at in think-prompt fact serialization by @nicoloboschi in #929
- feat: add OpenRouter support for LLM, embeddings, and reranking by @nicoloboschi in #930
- chore: drop hindsight-hermes integration by @nicoloboschi in #931
- feat: add retain update_mode='append' for document content concatenation by @nicoloboschi in #932
- feat: add built-in llama.cpp LLM provider for local inference by @nicoloboschi in #933
- feat(openclaw): add configurable retain tags by @Aldoustheorchestrator in #937
- fix: exclude local-llm from [all] extra by @nicoloboschi in #936
- Add Codex persistent memory blog post by @benfrank241 in #812
New Contributors
- @isac322 made their first contribution in #861
- @Spectorisimo made their first contribution in #875
- @Abdulkadirklc made their first contribution in #821
- @Aldoustheorchestrator made their first contribution in #910
- @mango766 made their first contribution in #908
Full Changelog: v0.4.22...v0.5.0