This withdraws our OpenClaw integration claims. Checked against OpenClaw's own source and docs (v2026.2.26 through the latest, v2026.9.6), the integration never worked with any OpenClaw release:
The documented config was never valid.memory.backend: "clawhdf5" wasn't accepted from v2026.2 to v2026.7, which allowed only builtin or qmd and rejected unknown keys, so a Gateway given our config refuses to start. v2026.8.1 ("OpenClaw 2.0") removed the key.
No plugin was ever built: no manifest, no registration, no tools, and no code read the documented config. Nothing was tested against OpenClaw.
The links and package weren't real: the linked github.com/redclawsystems/openclaw is a 404, and @redclaw/clawhdf5 was never published.
Decision: we're not pursuing an OpenClaw plugin for now. ZeroClaw is the integration target.
Changes (docs only; no code behaviour changes)
Removedopenclaw-integration.md, openclaw-config.md and migration-guide.md. They all rest on the invalid config.
Addeddocs/openclaw.md, covering:
the status and why;
what a real memory plugin needs against v2026.9.6: plugins.slots.memory, a manifest with kind: "memory", registerMemoryCapability with a MemorySearchManager, and prebuilt native packages;
what this repo already has as building blocks.
Reworded the README, QUICKSTART, USE_CASES, ROADMAP (Track 7 marked withdrawn), CLAUDE.md and the openclaw module docs. ClawhdfBackend is now described as what it is: a Markdown-oriented library API, not an OpenClaw plugin. The QUICKSTART example called a three-argument create that doesn't exist; it's corrected, with its limits stated.
Node package:packages/clawhdf5-node is marked unpublished and broken, and set private: true so it can't be published by accident. Its bugs are recorded in docs/known-issues.md: snake_case field names where napi-rs produces camelCase, the wrong addon path, no way to store an embedding, and the wrong WAL file name.
## Summary
This withdraws our OpenClaw integration claims. Checked against OpenClaw's own source and docs (v2026.2.26 through the latest, v2026.9.6), the integration never worked with any OpenClaw release:
- **The documented config was never valid.** `memory.backend: "clawhdf5"` wasn't accepted from v2026.2 to v2026.7, which allowed only `builtin` or `qmd` and rejected unknown keys, so a Gateway given our config refuses to start. v2026.8.1 ("OpenClaw 2.0") removed the key.
- **No plugin was ever built:** no manifest, no registration, no tools, and no code read the documented config. Nothing was tested against OpenClaw.
- **The links and package weren't real:** the linked `github.com/redclawsystems/openclaw` is a 404, and `@redclaw/clawhdf5` was never published.
**Decision:** we're not pursuing an OpenClaw plugin for now. ZeroClaw is the integration target.
### Changes (docs only; no code behaviour changes)
- **Removed** `openclaw-integration.md`, `openclaw-config.md` and `migration-guide.md`. They all rest on the invalid config.
- **Added** `docs/openclaw.md`, covering:
- the status and why;
- what a real memory plugin needs against v2026.9.6: `plugins.slots.memory`, a manifest with `kind: "memory"`, `registerMemoryCapability` with a `MemorySearchManager`, and prebuilt native packages;
- what this repo already has as building blocks.
- **Reworded** the README, QUICKSTART, USE_CASES, ROADMAP (Track 7 marked withdrawn), CLAUDE.md and the `openclaw` module docs. `ClawhdfBackend` is now described as what it is: a Markdown-oriented library API, not an OpenClaw plugin. The QUICKSTART example called a three-argument `create` that doesn't exist; it's corrected, with its limits stated.
- **Node package:** `packages/clawhdf5-node` is marked unpublished and broken, and set `private: true` so it can't be published by accident. Its bugs are recorded in `docs/known-issues.md`: snake_case field names where napi-rs produces camelCase, the wrong addon path, no way to store an embedding, and the wrong WAL file name.
- **Rustdoc:** two broken doc links fixed.
## Test plan
- [x] fmt, clippy `-D warnings` (agent, napi), 43 `openclaw` module tests
- [x] No links to the removed docs remain
- [ ] Gitea CI on this PR
🤖 Generated with [Claude Code](https://claude.com/claude-code)
The docs described a "drop-in" OpenClaw memory backend enabled with
`memory.backend = "clawhdf5"`. Checked against OpenClaw's source and
docs (v2026.2.26 through v2026.9.6): that config was never valid —
v2026.2-v2026.7 accepted only "builtin"/"qmd" and rejected unknown
keys, so a Gateway given it refuses to start, and v2026.8.1 (OpenClaw
2.0) removed the key. No plugin was ever built (no manifest, no
registration, no tools), nothing was tested against OpenClaw, the
linked github.com/redclawsystems/openclaw is a 404, and
@redclaw/clawhdf5 was never published.
Decision (2026-09-25): not pursuing an OpenClaw plugin for now; ZeroClaw
is the integration target.
- Remove openclaw-integration.md, openclaw-config.md and
migration-guide.md; add docs/openclaw.md: the status, what a memory
plugin needs against v2026.9.6 (plugins.slots.memory, manifest with
kind "memory", registerMemoryCapability / MemorySearchManager,
prebuilt native packages), and what this repo has as building blocks.
- README, QUICKSTART, USE_CASES, ROADMAP (Track 7 withdrawn), CLAUDE.md
and the `openclaw` module docs describe ClawhdfBackend as what it is:
a Markdown-oriented library backend, not an OpenClaw plugin. The
QUICKSTART example is corrected (the old one called a three-argument
create that does not exist) and states its limits.
- packages/clawhdf5-node: marked unpublished and broken, "private": true
so it cannot be published by accident; its bugs (snake_case vs
camelCase fields, wrong addon path, no way to store an embedding,
wrong WAL name) are recorded in docs/known-issues.md.
- Two broken rustdoc links fixed along the way.
Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
osobh
merged commit 79dfa78e8f into main2026-09-25 16:14:37 +00:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Summary
This withdraws our OpenClaw integration claims. Checked against OpenClaw's own source and docs (v2026.2.26 through the latest, v2026.9.6), the integration never worked with any OpenClaw release:
memory.backend: "clawhdf5"wasn't accepted from v2026.2 to v2026.7, which allowed onlybuiltinorqmdand rejected unknown keys, so a Gateway given our config refuses to start. v2026.8.1 ("OpenClaw 2.0") removed the key.github.com/redclawsystems/openclawis a 404, and@redclaw/clawhdf5was never published.Decision: we're not pursuing an OpenClaw plugin for now. ZeroClaw is the integration target.
Changes (docs only; no code behaviour changes)
openclaw-integration.md,openclaw-config.mdandmigration-guide.md. They all rest on the invalid config.docs/openclaw.md, covering:plugins.slots.memory, a manifest withkind: "memory",registerMemoryCapabilitywith aMemorySearchManager, and prebuilt native packages;openclawmodule docs.ClawhdfBackendis now described as what it is: a Markdown-oriented library API, not an OpenClaw plugin. The QUICKSTART example called a three-argumentcreatethat doesn't exist; it's corrected, with its limits stated.packages/clawhdf5-nodeis marked unpublished and broken, and setprivate: trueso it can't be published by accident. Its bugs are recorded indocs/known-issues.md: snake_case field names where napi-rs produces camelCase, the wrong addon path, no way to store an embedding, and the wrong WAL file name.Test plan
-D warnings(agent, napi), 43openclawmodule tests🤖 Generated with Claude Code