* feat: add @vectorize-io/hindsight-embed daemon lifecycle package
Create a new top-level `hindsight-embed-npm/` package that owns the daemon
lifecycle for the Python `hindsight-embed` CLI: spawning via `uvx`, writing
the profile, waiting for `/health`, and shutting down. Nothing more.
Deliberately does not ship an HTTP client — `@vectorize-io/hindsight-client`
already covers retain / recall / reflect / createBank against the Hindsight
API, and the two packages compose: once `manager.start()` returns, consumers
talk to the daemon via `new HindsightClient({ baseUrl: manager.getBaseUrl() })`.
`HindsightEmbedManagerOptions.env` forwards an arbitrary `Record<string,
string>` to both the daemon process and the profile config via `--env K=V`,
and `extraProfileCreateArgs` / `extraDaemonStartArgs` escape hatches cover
any new CLI flag without waiting for a wrapper release.
Refactor `hindsight-integrations/openclaw` to consume both packages:
`HindsightEmbedManager` for daemon lifecycle in local mode, `HindsightClient`
for all HTTP memory operations. Drop the bespoke subprocess/HTTP client that
used to live in openclaw. The retain queue stays local to openclaw (it's a
client-side reliability workaround with a single consumer today — will move
to the client package or server-side when a second consumer needs it).
Wire the new package into the main release pipeline (versioned alongside
the other core packages, published from `v*` tags) and add a CI build job.
* docs: add Embedded Node.js SDK page for @vectorize-io/hindsight-embed
* refactor: rename hindsight-embed-npm to hindsight-all, restructure docs sidebar
The Node package previously named @vectorize-io/hindsight-embed was
semantically misnamed: hindsight-embed (Python) is a CLI tool, while what
this Node package actually provides is the Node equivalent of hindsight-all
— a programmatic lifecycle manager for a local Hindsight daemon. Rename to
match.
Package rename
- hindsight-embed-npm/ → hindsight-all-npm/ (git mv, history preserved)
- @vectorize-io/hindsight-embed → @vectorize-io/hindsight-all
- class HindsightEmbedManager → HindsightServer (matches Python hindsight-all)
- HindsightEmbedManagerOptions → HindsightServerOptions
- src/manager.ts → src/server.ts, src/manager.test.ts → src/server.test.ts
- openclaw (index.ts, backfill.ts, tests) and the claude-code Python port
updated to reference the new names
Docs restructure
- Split sdks/python.md: now client-only content. New sdks/hindsight-all.md
covers the programmatic hindsight-all Python package (HindsightServer and
HindsightEmbedded).
- Rename sdks/embed-npm.md → sdks/hindsight-all-npm.md with HindsightServer
examples.
- New "Installation" sidebar section, placed after Hosting, containing
Docker / Kubernetes / Bare Metal (anchor links into developer/installation)
plus Programmatic API (Python), Programmatic API (Node.js), and Daemon CLI.
- Add si-docker, si-kubernetes, si-nodedotjs, lu-hard-drive to the sidebar
ICON_MAP.
Docs dev-server fix
- docusaurus.config.ts: drop the flaky NODE_ENV sniff for including the
"Next" version. Use INCLUDE_CURRENT_VERSION exclusively. NODE_ENV was
unreliable across hot-reload paths and caused the Next version to
disappear intermittently when editing files.
- scripts/dev/start-docs.sh: export INCLUDE_CURRENT_VERSION=true so local
dev always shows Next; production builds leave it unset.
Lockfile cleanup
- package-lock.json and hindsight-integrations/openclaw/package-lock.json
had extraneous hindsight-embed-npm blocks left over from the rename.
Removed manually and verified with npm install.
* ci: fix openclaw jobs by pre-building workspace deps; regenerate docs-skill
The build-openclaw-integration and test-openclaw-integration jobs failed
with "Failed to resolve entry for package @vectorize-io/hindsight-all"
because openclaw depends on two monorepo workspaces via `file:` deps
(@vectorize-io/hindsight-client and @vectorize-io/hindsight-all) whose
`dist/` directories are gitignored and never built before openclaw's npm ci.
Both jobs now install the root workspace and build the two deps first,
mirroring the release-control-plane pattern.
Also regenerate skills/hindsight-docs/references/* via
./scripts/generate-docs-skill.sh:
- new skill pages for sdks/hindsight-all{.md,-npm.md}
- updated skill pages for sdks/embed.md and sdks/python.md to match
the new H1s and split content
- incidental refreshes to changelog/index.md, developer/models.md,
openapi.json, and uv.lock that verify-generated-files picked up
* ci: build openclaw before running tests so symlink test can realpath dist
4.9 KiB
| sidebar_position |
|---|
| 6 |
Programmatic API (Node.js)
The @vectorize-io/hindsight-all npm package is the Node.js equivalent of the Python hindsight-all package. It lets your Node code spawn and supervise a local Hindsight daemon without deploying any server infrastructure — pair it with @vectorize-io/hindsight-client for memory operations.
The daemon runs as a separate OS process on 127.0.0.1 (not in your Node process). Your code talks to it over HTTP via HindsightClient.
This package does not ship an HTTP client — it only owns the server process. Once the daemon is running, talk to it with @vectorize-io/hindsight-client against server.getBaseUrl(). The two packages compose: one owns the process, the other owns the API surface.
How it works
server.start()resolves the underlyinghindsight-embedcommand (viauvxfrom PyPI, oruv run --directory <path>for a local checkout).- Runs
profile create <name> --merge --port <port> [--env KEY=VALUE ...]with every entry fromoptions.envforwarded as--env. - Runs
daemon --profile <name> start. - Polls
http://host:port/healthuntil it returns200or thereadyTimeoutMsbudget is exhausted. server.stop()runsdaemon --profile <name> stop.
The server is intentionally transparent: new daemon env vars or CLI flags never require a wrapper release — pass them through env, extraProfileCreateArgs, or extraDaemonStartArgs.
Requirements
- Node.js ≥ 22 — uses global
fetchandAbortSignal.timeout. uv/uvxonPATH— used to download and run the Hindsight daemon. Install via docs.astral.sh/uv.
Install
npm install @vectorize-io/hindsight-all @vectorize-io/hindsight-client
Example
import { HindsightServer, consoleLogger } from '@vectorize-io/hindsight-all';
import { HindsightClient } from '@vectorize-io/hindsight-client';
const server = new HindsightServer({
profile: 'my-app',
port: 9077,
env: {
HINDSIGHT_API_LLM_PROVIDER: 'anthropic',
HINDSIGHT_API_LLM_API_KEY: process.env.ANTHROPIC_API_KEY,
HINDSIGHT_API_LLM_MODEL: 'claude-sonnet-4-20250514',
HINDSIGHT_EMBED_DAEMON_IDLE_TIMEOUT: '0',
},
logger: consoleLogger,
});
await server.start();
const client = new HindsightClient({ baseUrl: server.getBaseUrl() });
await client.retain('user-123', 'User prefers dark mode.');
const recall = await client.recall('user-123', 'what are the user preferences?');
await server.stop();
For a remote Hindsight API, skip the server entirely and point HindsightClient directly at the remote URL.
HindsightServerOptions
| Option | Type | Default | Description |
|---|---|---|---|
profile |
string |
"default" |
Profile name passed to --profile on every sub-command. |
port |
number |
8888 |
TCP port the daemon listens on. |
host |
string |
"127.0.0.1" |
Hostname the daemon binds to (used for health checks). |
embedVersion |
string |
"latest" |
Version of the underlying hindsight-embed package to run via uvx. |
embedPackagePath |
string |
— | Local checkout path — takes precedence over embedVersion. Uses uv run --directory instead of uvx. |
env |
Record<string, string | undefined> |
{} |
Environment variables passed to the daemon process and written into the profile config via --env KEY=VALUE. The preferred way to surface any HINDSIGHT_API_* / HINDSIGHT_EMBED_* setting. |
extraProfileCreateArgs |
string[] |
[] |
Extra args appended verbatim to profile create. |
extraDaemonStartArgs |
string[] |
[] |
Extra args appended verbatim to daemon start. |
platformCpuWorkaround |
boolean |
true on macOS |
Auto-set HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU=1 and HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU=1 to avoid Metal/MPS crashes. Caller-supplied env values win over the auto-applied ones. |
readyTimeoutMs |
number |
30000 |
Max time to wait for /health to return 200. |
readyPollIntervalMs |
number |
1000 |
Polling interval while waiting for /health. |
logger |
Logger |
silent | Pluggable logger (debug/info/warn/error). consoleLogger and silentLogger helpers are exported. |
Server methods
| Method | Returns | Description |
|---|---|---|
start() |
Promise<void> |
Configure profile, spawn the daemon, wait for /health. Idempotent — safe to re-run. |
stop() |
Promise<void> |
Stop the daemon. Never throws; logs and resolves even on failure. |
checkHealth() |
Promise<boolean> |
One-shot /health probe with a 2 s timeout. |
getBaseUrl() |
string |
http://host:port — pass this straight to HindsightClient. |
getProfile() |
string |
The profile name this server operates on. |
For memory operations (retain, recall, reflect, bank management) use @vectorize-io/hindsight-client.