v1.0.0
CoreBunch/Instaticv1.0.0Oct 13, 2026by github-actions[bot]
Upgrading?
Key Highlights
- Multi-Provider Auto-Routing with zero configuration
- Problem Restate Gate to catch wrong-question failures
- Verdict Templates reordered to prioritize unresolved questions
- 3 Deliberation Modes: Full, Quick, and Duo
New Features
- Multi-Provider Auto-Routing (detects Claude, OpenAI, Google, Ollama)
- Problem Restate Gate
- Verdict Template Reordering
- Streamlined Protocol (consolidated enforcement steps)
- 3 Deliberation Modes
- 18 Council Members with specific domains and models
Full Release Notes
## What's Changed * fix(docs): overview hero reaches the window edges on wide screens by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5440 * docs: changelog and blog post for v0.10.3 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5435 * docs: fix the home page link preview by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5441 * docs(blog): plain post titles with a description subtitle and byline row by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5460 * fix(ui): hide the no-op '+field' button at the entity-label root level by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/5450 * refactor(openclaw)!: remove the agent-sdk package and the agent_knowledge_* tools by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5462 * fix(api): refuse tag-scoped callers on operations answered for the whole bank by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/5463 * docs(grok-bot): the marketplace listing is not approved yet by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/5465 * blog: Grok Bot Can Read What Your Other AI Tools Already Learned by @benfrank241 in https://github.com/vectorize-io/hindsight/pull/5461 * chore(deps): bump handlebars to 4.7.10 in eliza integration by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/5482 * chore(deps): bump pydantic-ai-slim to 1.107.7 in pydantic-ai integration by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/5483 * chore(deps): bump banks to 2.5.1 in llamaindex integration by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/5484 * chore(deps): bump handlebars to 4.7.10 in root lockfile by @cdbartholomew in https://github.com/vectorize-io/hindsight/pull/5481 * fix(integrations): claude-code chunk loss + timestamps, cursor Windows hooks, zed native MCP url by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5506 * fix(coding-agents): Windows hooks and spawns, pi session cwd, git log parsing by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5511 * fix(openclaw): drop the bankMission schema default so it stops overwriting bank missions by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5512 * fix(coding-agents): session-start survey/reflect gating, shared-bank page scope, initiative markers by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5510 * fix(coding-agents): memory injection on long prompts, empty first recalls, dsh repeats and Grok Build by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5514 * fix(openclaw): retain from plugin copies OpenClaw never started by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5517 * fix(control-plane): fix the next build type error in the entity-labels editor by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5518 * fix(coding-agents): keep retained sessions whole (pi runs, failed ops, exit, btw sessions, codex startup) by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5508 * fix(openclaw): read the ended transcript through OpenClaw's reader on session_end by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5522 * fix(api): consolidation discovery probe, mental-model edit race, LlamaParse v2 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5513 * docs(hermes): complete and correct the config reference by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5521 * feat(integrations): every integration identifies itself with its own User-Agent by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5466 * fix(clients,cli): forward-compatible decoding and bounded export polling by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5515 * fix(coding-agents): HTTP error handling in drain, reflect, page latch, append probe, long reflects by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5509 * fix(hermes): six plugin bugs that need no behaviour change by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5523 * test(retain): judge agent-experience classification instead of counting fact types by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5525 * fix(openclaw): capture inbound identity on message_received so Goals can start by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5530 * docs(meta-muse): link the changelog from the integration page by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5533 * fix(openclaw): honour logLevel and logSummaryIntervalMs by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5532 * fix(retain): merge JSON-array appends to a new document into one array by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5529 * fix(hermes): batch of small plugin bugs from #4662 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5534 * feat(openclaw): register as OpenClaw's native memory provider by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5535 * fix(api): retain prose 'no facts', claude-code JSON repair, codex stream errors, provider spans, claude-code ToS docs by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5516 * fix(api): a store that sheds a request answers 503 + Retry-After, not 500 by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5527 * fix(hermes): skip cron runs, honour HINDSIGHT_BANK_ID, add reflect_tags, re-probe an unreachable server by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5538 * test(worker): poll until drained in the concurrent-claim test by @nicoloboschi in https://github.com/vectorize-io/hindsight/pull/5537 **Full Changelog**: https://github.com/vectorize-io/hindsight/compare/v0.10.3...v1.0.0
Related Repositories
openclaw/openclaw★ 392,690
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,064
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 357,493
Reverse engineer anything with agents, from app behavior down to native binaries.
anomalyco/opencode★ 219,655
The open source coding agent.
n8n-io/n8n★ 208,248
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.