Bundle Pluginstructural

Thalamus (plugin shim)v1.0.0

OpenClaw plugin shim for Thalamus. Wires the MCP server provided by the openclaw-thalamus npm package (auto-installed as a dependency).

openclaw-thalamus-plugin·runtime openclaw-thalamus-plugin·by @msbel5

openclaw bundles install clawhub:openclaw-thalamus-plugin

Latest release: v1.0.0Download zip

Capabilities

Bundle format

clawpack

Compatibility

Built With Open Claw Version

2026.5.4

Plugin Api Range

>=2026.0.0

Security Scan

VirusTotal

Benign

View report →

OpenClaw

Benign

medium confidence

✓

Purpose & Capability

The name and description match the contents: the included code only registers a plugin ID and configuration schema, while the actual MCP server is explicitly delegated to the declared `openclaw-thalamus` npm dependency. The config fields for encoder host/port, vector store, packet store, and dashboard are consistent with a local MCP/cognitive-routing tool.

✓

Instruction Scope

The SKILL.md instructions stay within the stated purpose: install the plugin, add an MCP server entry for `openclaw-thalamus-mcp` to `~/.openclaw/openclaw.json`, and restart the user gateway. It does not instruct the agent to read unrelated files, collect unrelated data, access undeclared environment variables, or send data to unexpected endpoints.

ℹ

Install Mechanism

There is no separate install spec, but `package.json` declares an npm dependency on `openclaw-thalamus` and the documentation says it will be auto-installed. Pulling from npm is a normal, traceable mechanism, but it means this is not purely instruction-only and the main behavior lives in a package not included in this review.

✓

Credentials

The skill declares no required environment variables, credentials, tokens, or config-path requirements. The instructions also do not access undeclared secrets. This is proportionate for a local plugin shim.

✓

Persistence & Privilege

`always` is false, the plugin is not enabled by default, and there is no evidence it modifies other skills or system-wide settings beyond the expected OpenClaw MCP server wiring. Autonomous model invocation is the platform default and is not a concern by itself.

Assessment

The shim itself looks coherent and minimal. The main thing to check before installing is the separate `openclaw-thalamus` npm package, because that package provides the MCP server, CLI, and optional dashboard that will actually run. If you trust that upstream package and expect a local Thalamus MCP server to be added to OpenClaw, the requested behavior matches the stated purpose.

Verification

Tier

structural

Scope

artifact only

Summary

Validated package structure and extracted metadata.

Scan status

clean

Thalamus (plugin shim)

This is the OpenClaw plugin shim for Thalamus. It is small on purpose: it declares the plugin manifest, validates the config stanza, and exists so OpenClaw can wire Thalamus through its plugin system. The actual work, the MCP server and the cognitive routing layer, is in the separate openclaw-thalamus npm package, which is declared as a dependency here and is auto-installed when you install this plugin.

If you only want the MCP server and you do not care about the OpenClaw plugin manifest, install openclaw-thalamus directly via npm and skip this package.

What gets installed

clawhub:openclaw-thalamus-plugin   ← this package (the shim)
       └── npm dep: openclaw-thalamus ^1.0.1   ← the MCP server, CLI, dashboard

Install (recommended)

openclaw plugins install clawhub:openclaw-thalamus-plugin

OpenClaw fetches the shim, then runs npm install of the declared dependency, which pulls openclaw-thalamus@^1.0.1 from npm. After install, you have:

openclaw-thalamus (CLI: health, context, benchmark)
openclaw-thalamus-mcp (MCP server binary)
openclaw-thalamus-dashboard (optional HTTP dashboard)

Wire the MCP server

Append to ~/.openclaw/openclaw.json:

{
  "mcpServers": [
    { "name": "thalamus", "command": "openclaw-thalamus-mcp" }
  ]
}

Restart the gateway:

systemctl --user restart openclaw-gateway

The MCP tools thalamus_route, thalamus_resolve, thalamus_search, thalamus_search_with_vector, thalamus_promote_packet, thalamus_telemetry should now appear in the OpenClaw tool registry.

Plugin config

The openclaw.plugin.json schema accepts the following config under plugins.entries.openclaw-thalamus-plugin.config:

Field	Default	Purpose
`encoderHost`	`127.0.0.1`	Host of the local Qwen3 encoder daemon, if running
`encoderPort`	`28760`	Port of the encoder daemon
`vectorStorePath`	`~/.openclaw/state/thalamus/vectors`	FAISS + BBQ codebook directory
`packetStorePath`	`~/.openclaw/state/thalamus/packets`	Content-addressed packet store
`dashboardEnabled`	`false`	Enable HTTP telemetry dashboard
`dashboardPort`	`28761`	Dashboard HTTP port

The shim itself does not start any process. OpenClaw spawns the MCP server based on the mcpServers entry in openclaw.json. The encoder daemon (CPU Qwen3 via llama.cpp) is started separately if you want it; see the upstream openclaw-thalamus README for scripts/install-encoder.sh.

Honest measurements

The directly measured numbers from a Pi 5 production run live in BENCHMARKS.md on the upstream repo:

Protocol-level token compression (the @-code layer): 19.1% reduction on Captain spawn context (spawn_context_tokens 68 to compact_context_tokens 55, three rows in run_telemetry.jsonl).
BBQ codebook on 99,823 vectors: mean cosine 0.978, p10 0.985, p50 0.999.
Qwen3-Embedding-0.6B Q4_0 GGUF warm latency: about 167 ms p50 on Pi 5 CPU.

The combined "packet handoff plus protocol" figure quoted in earlier README drafts is a single-machine direction signal, not a benchmark, because there is no side-by-side run against a naive transcript paste baseline. Take that one with a grain of salt; the 19.1 percent figure has a real before-and-after on the same workload.

License

MIT. Source code for the shim and the MCP server live in the same upstream repo: https://github.com/msbel5/openclaw-thalamus