v0.7.0
vectorize-io/hindsightv0.7.0May 27, 2026by github-actions[bot]
Upgrading?
Release notes summary
Introduces Opencode-go, BM25 improvements with configurable language, Paperclip per-user isolation, and ParadeDB pg_search backend.
Key Highlights
- Opencode-go LLM provider
- Configurable BM25 language backend
- Paperclip per-user memory isolation
- ParadeDB pg_search backend
- Zeroentropy embeddings provider
New Features
- Opencode-go LLM provider
- BM25 configurable native language
- Paperclip per-user memory isolation
- ParadeDB pg_search backend
- Zeroentropy embeddings provider
- TypeScript client type safety improvements
Full Release Notes
## What's Changed * docs: add 0.6.2 changelog and release blog post by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1633 * docs: attribute 0.6.2 release post to benfrank241 by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1635 * blog: What's New in Hindsight Cloud by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1636 * feat(typescript-client): replace Promise<any> with concrete generated types by @solidprinciples in https://github.com/vectorize-io/hindsight/pull/1640 * docs(changelog): correct openai-agents v0.1.1 entry by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1639 * docs: add HINDSIGHT_API_WORKER_ID tip to API quickstart by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1617 * fix(api): strip Gemma thought tags by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1653 * feat: add opencode-go LLM provider by @tevenfeng in https://github.com/vectorize-io/hindsight/pull/1652 * fix(api): lazy load reflect tiktoken encoding by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1654 * fix(api): preserve tag group or triggers by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1655 * fix(api): auto-refresh openai-codex OAuth access_token by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1661 * fix(typescript-client): update repository URL to correct repo by @solidprinciples in https://github.com/vectorize-io/hindsight/pull/1657 * Blog: Agent Memory Consolidation framework by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1672 * style: apply ruff format to openai_compatible_llm.py by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1703 * docs(crewai): prioritize Hindsight Cloud in quickstart by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1689 * docs(strands): prioritize Hindsight Cloud in quickstart by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1690 * docs(pipecat): prioritize Hindsight Cloud in quickstart by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1695 * Regenerate hindsight-docs skill references by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1686 * docs(pydantic-ai): prioritize Hindsight Cloud in quickstart by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1691 * docs(smolagents): prioritize Hindsight Cloud in quickstart by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1692 * docs(codex): add Cloud API URL to quickstart and config default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1693 * docs(agentcore): add Cloud API URL to quickstart and config default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1694 * docs(agno): add Cloud API URL to quickstart and config default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1696 * docs(n8n): add Cloud API URL to quickstart and config default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1697 * docs(dify): add Cloud API URL to quickstart and config default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1698 * docs(paperclip): add Cloud API URL to quickstart and config default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1699 * docs(nemoclaw): add Cloud API URL to quickstart and config default by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1700 * docs(chat): add Cloud API URL to quickstart by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1701 * fix(api): ignore null bank config overrides by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1664 * fix(api): reject blank retain content by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1685 * fix: derive HINDSIGHT_API_HEALTH_URL default from HINDSIGHT_API_PORT by @sg-shag in https://github.com/vectorize-io/hindsight/pull/1709 * fix(mcp): omit reflect provenance by default by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1665 * fix: break mutual recursion in batch API fallback for non-batch providers by @mssteuer in https://github.com/vectorize-io/hindsight/pull/1463 * feat(reranker): support alibaba qwen3-rerank by @quicklyfast in https://github.com/vectorize-io/hindsight/pull/1501 * feat(extensions): add OperationValidator.precheck pre-body-parse hook by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/1548 * fix(claude-code-mcp): make run_mcp.sh bootstrap idempotent on Windows by @ottopichlhoefer in https://github.com/vectorize-io/hindsight/pull/1565 * fix(integrations-claude-code): label 'Current time' as UTC in recall context by @valda in https://github.com/vectorize-io/hindsight/pull/1568 * fix(reranker): detect pre-normalized scores and use rank-based normalization by @xuli500177 in https://github.com/vectorize-io/hindsight/pull/1512 * feat(right-agent): add Right Agent integration by @onsails in https://github.com/vectorize-io/hindsight/pull/1599 * fix(docker): detect nested pg0 data directories by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1650 * chore(deps): bump openssl from 0.10.79 to 0.10.80 in /hindsight-clients/rust in the cargo group across 1 directory by @dependabot[bot] in https://github.com/vectorize-io/hindsight/pull/1663 * fix(helm): remove stale Chart.lock that pulls in conflicting Bitnami postgresql sub-chart by @jay-mtl in https://github.com/vectorize-io/hindsight/pull/1632 * fix(mental-models): cap history array length to prevent jsonb overflow by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/1593 * fix(control-plane): surface upstream errors via respondWithSdk helper by @offendingcommit in https://github.com/vectorize-io/hindsight/pull/1678 * fix(embed): resolve npx absolute path on Windows before spawning UI by @tuancookiez-hub in https://github.com/vectorize-io/hindsight/pull/1682 * fix: escape literal braces in all user-supplied prompt fields by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1728 * fix(mental-models): full refresh pending delta baselines by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1684 * fix: avoid retrying invalid embedding dimensions by @ai-ag2026 in https://github.com/vectorize-io/hindsight/pull/1687 * chore(deps): bump the uv group across 2 directories with 2 updates by @dependabot[bot] in https://github.com/vectorize-io/hindsight/pull/1705 * fix(openclaw): update Hindsight dependency ranges by @de1tydev in https://github.com/vectorize-io/hindsight/pull/1716 * fix(worker): handle stale pending schema routines by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1666 * fix(api): enable gzip middleware to keep graph payload parseable by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1731 * fix(docs): correct DATABASE_URL env var name and fix invisible code in tip titles by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1733 * fix(control-plane): verify signed session cookie instead of presence by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1739 * fix: skip fuzzy entity resolution for user-defined label entities (#1558) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1737 * fix(api): wire up per-operation LLM concurrency caps by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1738 * docs(blog): Hermes coding assistant codebase memory by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1710 * fix(retain): split oversized single items in batch retain (#1571) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1736 * feat(api): add clear endpoint for mental model content by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1743 * test: stabilize pre-existing CI flakes by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1742 * fix(api): make litellm-sdk embeddings api_key optional for Bedrock IAM auth by @jakub-qg in https://github.com/vectorize-io/hindsight/pull/1744 * fix(reflect): hide disabled tools from the agent's system prompt by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1740 * fix(ollama): add ollama-cloud provider and fix native API auth by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1734 * feat(api): add targeted consolidation by observation scopes by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1746 * fix(api): release glibc heap pages after local reranker batches by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1745 * docs(mcp): document clear_mental_model tool by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1750 * fix(api): ignore inherited v1 base URL for Codex by @de1tydev in https://github.com/vectorize-io/hindsight/pull/1718 * fix(webhooks): avoid duplicate retain batch deliveries by @xmh1011 in https://github.com/vectorize-io/hindsight/pull/1683 * fix(api): stop sending temperature param to Anthropic API by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1753 * feat(bm25): configurable native language + opt-in pgroonga backend by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1538 * feat: support Codex OAuth embeddings by @haha0815 in https://github.com/vectorize-io/hindsight/pull/1704 * fix(ci): align config field count and CLI consolidation call with #1746 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1757 * chore(db): drop 9 unused/redundant indexes by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1762 * feat(control-plane): surface clear_mental_model in UI by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1764 * feat(paperclip): add per-user memory isolation via bankGranularity by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1761 * feat(api): add ParadeDB pg_search as Citus-compatible BM25 backend by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1755 * docs: clarify region for S3-compatible file storage providers by @davidmyriel in https://github.com/vectorize-io/hindsight/pull/1760 * docs(blog): Paperclip persistent memory integration by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/1763 * feat(api): add HINDSIGHT_API_ACCESS_LOG env var by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1765 * perf(api): derive entity edges from unit_entities instead of materializing them by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1766 * fix: improve observation consolidation and reflect temporal reasoning by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1759 * docs(config): note litellm-sdk embeddings API key is optional for ambient credentials by @r266-tech in https://github.com/vectorize-io/hindsight/pull/1747 * [feature] add zeroentropy embeddings provider by @flamerged in https://github.com/vectorize-io/hindsight/pull/1770 * Split test suite into deterministic mock and real LLM buckets by @DK09876 in https://github.com/vectorize-io/hindsight/pull/1469 * test: stabilize two LLM-flake tests surfaced after PR #1469 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1774 * chore(api): clean up zeroentropy embeddings, dedup base URL with reranker by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1773 * feat(control-plane): add i18n support with 8 locales by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1775 * feat(api): add pg_search tokenizer configuration by @Sanderhoff-alt in https://github.com/vectorize-io/hindsight/pull/1776 * chore: improve hindsight maintenance path by @lphuc2250gma in https://github.com/vectorize-io/hindsight/pull/1777 * feat(api): async link recompute to fix outgoing-link staleness after deletes by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/1772 ## New Contributors * @solidprinciples made their first contribution in https://github.com/vectorize-io/hindsight/pull/1640 * @tevenfeng made their first contribution in https://github.com/vectorize-io/hindsight/pull/1652 * @sg-shag made their first contribution in https://github.com/vectorize-io/hindsight/pull/1709 * @mssteuer made their first contribution in https://github.com/vectorize-io/hindsight/pull/1463 * @quicklyfast made their first contribution in https://github.com/vectorize-io/hindsight/pull/1501 * @ottopichlhoefer made their first contribution in https://github.com/vectorize-io/hindsight/pull/1565 * @valda made their first contribution in https://github.com/vectorize-io/hindsight/pull/1568 * @xuli500177 made their first contribution in https://github.com/vectorize-io/hindsight/pull/1512 * @onsails made their first contribution in https://github.com/vectorize-io/hindsight/pull/1599 * @jay-mtl made their first contribution in https://github.com/vectorize-io/hindsight/pull/1632 * @tuancookiez-hub made their first contribution in https://github.com/vectorize-io/hindsight/pull/1682 * @ai-ag2026 made their first contribution in https://github.com/vectorize-io/hindsight/pull/1687 * @de1tydev made their first contribution in https://github.com/vectorize-io/hindsight/pull/1716 * @jakub-qg made their first contribution in https://github.com/vectorize-io/hindsight/pull/1744 * @haha0815 made their first contribution in https://github.com/vectorize-io/hindsight/pull/1704 * @davidmyriel made their first contribution in https://github.com/vectorize-io/hindsight/pull/1760 * @flamerged made their first contribution in https://github.com/vectorize-io/hindsight/pull/1770 * @Sanderhoff-alt made their first contribution in https://github.com/vectorize-io/hindsight/pull/1776 * @lphuc2250gma made their first contribution in https://github.com/vectorize-io/hindsight/pull/1777 **Full Changelog**: https://github.com/vectorize-io/hindsight/compare/v0.6.2...v0.7.0
Related Repositories
public-apis/public-apis★ 491,660
A collective list of free APIs
NousResearch/hermes-agent★ 256,513
The agent that grows with you
yt-dlp/yt-dlp★ 200,929
A feature-rich command-line audio/video downloader
microsoft/markitdown★ 191,817
Python tool for converting files and office documents to Markdown.
Significant-Gravitas/AutoGPT★ 187,717
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.