Hindsight Files

What's Changed

• docs: changelog and blog post for v0.8.4 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2474
• fix(control-plane): show all mental models instead of capping at 100 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2512
• fix(codex): implement strict_schema via forced tool call + repair invalid \escape (#2504) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2513
• refactor(control-plane): drop the Graph view from memories by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2517
• Blog: Devin Desktop persistent memory (formerly Windsurf) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2483
• Update Devin Desktop blog cover image by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2524
• fix(control-plane) fix json viewer unicode output display by @ymybxx in https://github.com/vectorize-io/hindsight/pull/2531
• fix(control-plane): keep memory filters visible on empty results by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2532
• fix(curation): drop archive search_vector column, recompute on revert (#2503) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2514
• feat(control-plane): animate the memories constellation & open memories in a dialog by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2536
• test(retain): fix missing llm_temperature_retain in _build_request_body mock by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2537
• Blog: architxt + Hindsight (Temporal Mosaic) — community post by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2526
• feat(eve): auto-memory mode (v0.2.0) — no model tool-calling by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2527
• feat(eve): retain the assistant reply by default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2585
• Blog: Eve automatic memory (hindsight-eve v0.2.0) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2584
• fix(agent-sdk): release recall token fix as 0.1.1 by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2596
• Refresh search vector on memory curation edits by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2552
• docs(eve): sync assistant reply default by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2588
• fix(parsers): coerce non-bytes buffers before the UTF-8 charset probe in markitdown by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/2586
• fix(memory): return metadata from memory browse endpoints by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2583
• fix(retain): preserve JSON chunks during output retry by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2579
• fix(api): let PATCH /memories clear occurred dates with null by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2607
• feat(integrations): add recall score floors by @ishanmalik in https://github.com/vectorize-io/hindsight/pull/2575
• fix(opencode): install plugin SDK at runtime by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2574
• fix(api): accept verbatim extraction mode in bank manifests by @ishanmalik in https://github.com/vectorize-io/hindsight/pull/2576
• Fix chunk delete deadlock ordering by @oldnicke in https://github.com/vectorize-io/hindsight/pull/2570
• feat(recall): add opt-in BM25 query term cap by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2567
• fix(control-plane): build local client before production build by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2566
• docs(skill): sync configuration reference for BM25 term cap by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2609
• fix(consolidation): default invalid dedup actions to keep by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2565
• fix(cli): set default User-Agent header by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2564
• Fix _strip_code_fences truncating JSON when content contains inner backticks by @poog26 in https://github.com/vectorize-io/hindsight/pull/2563
• fix(minimax): disable thinking by default by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2558
• feat(llm): recover outer JSON span when fence stripping yields non-JSON by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2610
• refactor(zed): port setup CLI to Node, drop the Python dependency by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2599
• Blog: Give Zed's AI Assistant a Persistent Memory by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2598
• docs: add Oracle Database setup guide by @DK09876 in https://github.com/vectorize-io/hindsight/pull/2612
• fix(oracle): don't await the synchronous cursor.close() in _set_session_schema by @DK09876 in https://github.com/vectorize-io/hindsight/pull/2613
• docs(oracle): document required schema, embedding-dimension matching, and start-oracle re-run by @DK09876 in https://github.com/vectorize-io/hindsight/pull/2615
• fix(worker): complete successful operations by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2608
• fix(ollama): make native num_ctx opt-in by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2589
• fix(recall): decouple temporal seed threshold by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2595
• fix(reflect): tolerate null-like tool integer limits by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2639
• fix(claude-code): isolate MCP server cwd by @oldnicke in https://github.com/vectorize-io/hindsight/pull/2635
• fix(claude-code): skip primary + duplicate banks in recallAdditionalBanks by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2625
• Blog: Give Aider a Memory That Outlives the Session by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2642
• feat(anthropic): prompt caching via inline cache_control markers by @hb-cam in https://github.com/vectorize-io/hindsight/pull/2629
• feat(anthropic): implement the batch API interface via Message Batches (50% token discount) by @hb-cam in https://github.com/vectorize-io/hindsight/pull/2628
• fix: handle FK violation in observation_history during parallel consolidation by @handnewb in https://github.com/vectorize-io/hindsight/pull/2620
• fix(trace): skip LLM trace writes during daemon shutdown/pre-init races by @yingliang-zhang in https://github.com/vectorize-io/hindsight/pull/2618
• fix(codex): send client identity headers for GPT-5.6 by @JiehoonKwak in https://github.com/vectorize-io/hindsight/pull/2647
• Blog: One Memory, Three Surfaces (Cursor + OpenClaw + Vapi) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2655
• deps(security): require LiteLLM 1.84.0 by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2651
• fix(llm): raise OpenRouter Qwen3 verification budget by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2633
• fix(consolidation): normalize dedup action case/whitespace before validation by @iRonin in https://github.com/vectorize-io/hindsight/pull/2611
• Include cookbook and integration docs in docs skill by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2649
• Accept top-level fact arrays in retain parsing by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2556
• fix(recall): scope entity fanout cap by fact type by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2681
• Preserve document metadata during append retains by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2684
• fix(engine): clarify causal link compatibility by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2685
• fix(control-plane): forward document search q to dataplane by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2687
• fix(search): avoid year-0 crashes in Chinese rolling-window temporal extraction by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2636
• fix(control-plane): tag/scope filter resets during consolidation polling in data view by @viliusdidit in https://github.com/vectorize-io/hindsight/pull/2680
• fix(recall): preserve combined graph activation scores by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2679
• fix(consolidation): request JSON dedup decisions by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2663
• fix(migrations): install public maintenance routines on non-public schema runs by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2690
• Blog: Inside retain() — What Happens When Your Agent Remembers by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2689
• feat(devin-desktop): two-tier bank scoping + visible memory use (v0.2.0) by @DK09876 in https://github.com/vectorize-io/hindsight/pull/2692
• fix(worker): bound terminal operation history by @Tosko4 in https://github.com/vectorize-io/hindsight/pull/2708
• Fix Codex OAuth refresh sharing across managers by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2706
• fix(claude-code): surface the CLI's real error text on is_error results by @ElanHasson in https://github.com/vectorize-io/hindsight/pull/2703
• Avoid slim embedded daemon startup without local ML deps by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2676
• fix(claude-code): retain session deltas by @oldnicke in https://github.com/vectorize-io/hindsight/pull/2648
• docs(embed): expose local CPU workarounds by @yingliang-zhang in https://github.com/vectorize-io/hindsight/pull/2707
• fix(control-plane): show bank name (fallback bank_id) in bank selector by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2693
• fix(test): green main — update Oracle session-schema tests for [#2708] reset behavior by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2722
• fix(retain): recover recoverable batch-extraction JSON instead of dropping facts by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2720
• fix(gemini): grammar-enforce batch structured output regardless of strict flag by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2719
• fix reranker heap release after local scoring by @oldnicke in https://github.com/vectorize-io/hindsight/pull/2530
• fix(embed): green main — use --target sibling binary unconditionally (#2676 vs [#1240]) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2723
• feat(retain): optional fail-on-extraction-errors flag (issue [#2700]) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2721
• fix: coerce non-string metadata values to strings in MemoryFact.parse_metadata by @handnewb in https://github.com/vectorize-io/hindsight/pull/2623
• fix(openclaw): gate append retention on stored text by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/2511
• Blog: Give Every Agent You Run in Omnigent a Persistent Memory by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2709
• docs: Add Omnigent integration page by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2710
• chore(deps): bump langsmith and ws (security) by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2743
• chore(deps): migrate pipecat integration to pipecat-ai 1.x (clears 4 high-severity alerts) by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2380
• docs: fix conversation-scoped bank claim in Omnigent post by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2748
• chore(deps): npm transitive pins (1 critical + mediums) and pydantic-ai-slim by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2751
• blog: One Bank or Many? A Field Guide to Structuring Agent Memory by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2747
• fix(reflect): keep horizontal rules inside fenced code blocks by @ebarkhordar in https://github.com/vectorize-io/hindsight/pull/2755
• fix(entity-resolver): keep every co-occurrence pair when canonicalising order by @ebarkhordar in https://github.com/vectorize-io/hindsight/pull/2750
• fix(test): seed torch._inductor.test_operators to fix test-api shard failures by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2761
• test(fact-extraction): stop judging phrasing/attribution the system already captures by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2769
• fix(reflect): pair each expanded memory_id with its own memory by @ebarkhordar in https://github.com/vectorize-io/hindsight/pull/2759
• fix(openai): record cached and reasoning tokens on the LLM metrics counters by @ebarkhordar in https://github.com/vectorize-io/hindsight/pull/2758
• fix(reflect): preserve bank attribution in provider calls by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2764
• fix(embed): defer provider credential validation by @oldnicke in https://github.com/vectorize-io/hindsight/pull/2746
• fix(api): decode memory observation scopes by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2735
• test(openrouter): set cached-token fields in mock to stop intermittent MagicMock crash by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2776
• chore(deps): bump pydantic-settings, transformers, soupsieve (security) by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2727
• chore(deps): bump mcp to 1.28.1 (clears 20 high-severity MCP SDK alerts) by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2782
• docs(guides): add 44 integration memory guides by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2778
• blog: The Fully Open Agent Memory Stack (Hermes + Hindsight) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2771
• perf+fix(graph-maintenance): catch the [#2529] sweep deadlock in continuous perf, and drive dropped passes to zero by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2534
• fix(embeddings): truncate oversized litellm-sdk inputs before embedding (#2501) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2516
• fix(mcp): prevent get_bank from creating banks by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2393
• feat(auth): add create bank validation hook by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2395
• chore: remove stray local state files by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2472
• feat(reflect): step-by-step context caching for the Gemini tool loop by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2540
• fix(search): include proof_count in temporal spreading SQL SELECT by @Srujan-rai in https://github.com/vectorize-io/hindsight/pull/2479
• fix(reflect): thread max_completion_tokens into the structured-output extraction call (#2431) by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2486
• docs(cli): describe explore memory detail view by @koriyoshi2041 in https://github.com/vectorize-io/hindsight/pull/2497
• revert(docs-skill): drop cookbook pages from the docs skill bundle by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2818
• fix(control-plane): clear mental-model tags when the edit field is emptied (#2507) by @nicolas-vivot in https://github.com/vectorize-io/hindsight/pull/2508
• revert(migrations): drop advisory-lock maintenance-routines install (#2690) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2817
• fix(migrations): install maintenance routines into each run's own schema by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2820
• perf(graph-maintenance): prune stale cooccurrences via INTERSECT, not a self-join (7.1x, 289x fewer buffers) by @sergattic in https://github.com/vectorize-io/hindsight/pull/2473
• style: apply ruff format to reflect/agent.py by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2822
• feat(config): optional cap on planner parallelism for pool connections by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/2600
• feat(api): enrich refresh_mental_model result_metadata with semantic outcome by @hb-cam in https://github.com/vectorize-io/hindsight/pull/2627
• fix(trace): gate LLM trace writes on backend lifecycle, not error strings (reverts [#2618]) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2821
• feat(anthropic): carry the prompt-cache marker on batch system prompts by @hb-cam in https://github.com/vectorize-io/hindsight/pull/2652
• fix(recall): remove unused graph seed inputs by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2683
• fix(engine): consolidate duplicated engine definitions by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2691
• docs(retain): correct entity resolution (no nickname resolution) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2694
• fix(migrations): install the maintenance routines once, in the configured schema by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2824
• fix(engine): isolate operation completion from best-effort side-effects by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2823
• fix(reflect): preserve required tools for custom OpenAI endpoints by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2734
• fix(migrations): preserve percent-encoded database URLs by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2733
• fix(ci): avoid rebuilding docs in verify-generated-files by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2739
• feat(api): attribute remote reranker calls by bank by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2740
• fix(reflect): cap done tool answers by @Sanjays2402 in https://github.com/vectorize-io/hindsight/pull/2757
• Fix day+month+year dates collapsing to the whole month by @dimonnld in https://github.com/vectorize-io/hindsight/pull/2791
• feat(zcode): add Hindsight long-term memory integration for ZCode by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2549
• fix(query-analyzer): pick strongest dateparser match, not the leftmost (#2768) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2772
• fix(retain): reject degenerate fact text before storage (#2520) by @handnewb in https://github.com/vectorize-io/hindsight/pull/2794
• fix(audit): add missing @audited decorator to api_update_memory by @handnewb in https://github.com/vectorize-io/hindsight/pull/2798
• fix(retain): make lazy bank creation atomic (#2695) by @ijevin in https://github.com/vectorize-io/hindsight/pull/2802
• fix(db): re-apply session GUCs on pool acquire (asyncpg RESET ALL wipes them) by @sireika in https://github.com/vectorize-io/hindsight/pull/2815
• feat(pg0): carry optional user/password in pg0:// URLs by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2832
• test(recall): stop passing removed semantic_seeds into link expansion by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2829
• fix(retain): make entities a plain list of strings (#2749) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2830
• fix(worker): discover expired-operation schemas in one query, default retention off by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2819
• blog: Persistent memory for ZCode (Z.ai GLM coding agent) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2838
• fix: remove vulnerable API runtime packages by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2851
• chore(db): remove the dead advisory_lock dialect helper by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2855
• feat: add tags filtering to list_memories / list_memory_units by @superafun in https://github.com/vectorize-io/hindsight/pull/2848
• fix: disable built-in tools in ClaudeCodeLLM.call() to prevent ToolSearch deferral eating max_turns=1 by @peter216 in https://github.com/vectorize-io/hindsight/pull/2850
• fix(memory): preserve bank attribution during curation by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2847
• fix(llm): emit OpenAI strict JSON schemas by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2845
• feat(audit): make audit_log_enabled overridable per bank by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2827
• fix(retain): reassert resolved entities before linking units (#2662) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2859
• fix(pg0): honor URL credentials during MemoryEngine startup by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2836
• chore(deps): bump nltk to 3.10.0 (clears 2 high-severity path-traversal alerts) by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2833
• fix(retain): preserve fact alignment when filtering degenerate text by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2846
• Per-operation strict schema for consolidation by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2825
• fix(#2808): make mental model tags_match configurable on all creation surfaces (MCP, TS client, CLI) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2858
• fix(mental-models): align stale checks with refresh tag scope by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2804
• fix(retain): a zero retry budget must still perform the initial fact-extraction request by @chethanuk in https://github.com/vectorize-io/hindsight/pull/2779
• fix(integrations): keep auto-managed Hindsight daemons working on Python 3.14 hosts by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2801
• fix(opencode): derive session-start recall query from user messages (#2856) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2860
• fix(docker): build official images from the committed workspace lock by @r266-tech in https://github.com/vectorize-io/hindsight/pull/2789
• feat(api): allow deleting terminal bank operations with control-plane support by @chethanuk in https://github.com/vectorize-io/hindsight/pull/2777
• fix(transfer): preserve JSONB and timestamp provenance by @Korayem in https://github.com/vectorize-io/hindsight/pull/2717
• fix(worker): count crash-recovery attempts toward max-retry budget (#2675) by @handnewb in https://github.com/vectorize-io/hindsight/pull/2834
• fix(retain): queue retain.completed webhook on boundary and zero-fact batches by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2861
• fix(reflect): emit canonical OpenAI tool result messages by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2844
• fix: advance watermark after no-op delta refresh by @SunneeYang in https://github.com/vectorize-io/hindsight/pull/2866
• fix(cli): sync regenerated OpenAPI operation changes by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2867
• feat(llm): opt-in 4xx request-dump for diagnosing rejected calls (all providers) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2865
• fix(docs): sync generated documentation skill by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/2870
• fix(vector-index): repair per-bank index coverage after restore/upgrade (#2645) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2872
• refactor(llm): type provider tool choices by @Jordan-Jarvis in https://github.com/vectorize-io/hindsight/pull/2843
• fix(llm): recover malformed JSON via json_repair (last-resort parse fallback) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/2871
• chore(deps): pin adm-zip >=0.6.0 in zapier (clears last fixable high alert) by @dcbouius in https://github.com/vectorize-io/hindsight/pull/2880
• blog: Make Thinking Machines' Inkling your agent's memory (tutorial) by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/2882

New Contributors

• @ymybxx made their first contribution in https://github.com/vectorize-io/hindsight/pull/2531
• @ishanmalik made their first contribution in https://github.com/vectorize-io/hindsight/pull/2575
• @oldnicke made their first contribution in https://github.com/vectorize-io/hindsight/pull/2570
• @poog26 made their first contribution in https://github.com/vectorize-io/hindsight/pull/2563
• @hb-cam made their first contribution in https://github.com/vectorize-io/hindsight/pull/2629
• @handnewb made their first contribution in https://github.com/vectorize-io/hindsight/pull/2620
• @yingliang-zhang made their first contribution in https://github.com/vectorize-io/hindsight/pull/2618
• @JiehoonKwak made their first contribution in https://github.com/vectorize-io/hindsight/pull/2647
• @iRonin made their first contribution in https://github.com/vectorize-io/hindsight/pull/2611
• @viliusdidit made their first contribution in https://github.com/vectorize-io/hindsight/pull/2680
• @ElanHasson made their first contribution in https://github.com/vectorize-io/hindsight/pull/2703
• @ebarkhordar made their first contribution in https://github.com/vectorize-io/hindsight/pull/2755
• @Jordan-Jarvis made their first contribution in https://github.com/vectorize-io/hindsight/pull/2764
• @Srujan-rai made their first contribution in https://github.com/vectorize-io/hindsight/pull/2479
• @nicolas-vivot made their first contribution in https://github.com/vectorize-io/hindsight/pull/2508
• @sergattic made their first contribution in https://github.com/vectorize-io/hindsight/pull/2473
• @Sanjays2402 made their first contribution in https://github.com/vectorize-io/hindsight/pull/2757
• @dimonnld made their first contribution in https://github.com/vectorize-io/hindsight/pull/2791
• @ijevin made their first contribution in https://github.com/vectorize-io/hindsight/pull/2802
• @superafun made their first contribution in https://github.com/vectorize-io/hindsight/pull/2848
• @peter216 made their first contribution in https://github.com/vectorize-io/hindsight/pull/2850
• @chethanuk made their first contribution in https://github.com/vectorize-io/hindsight/pull/2779
• @SunneeYang made their first contribution in https://github.com/vectorize-io/hindsight/pull/2866

Full Changelog: https://github.com/vectorize-io/hindsight/compare/v0.8.4...v0.8.5