Signet-AI/signetai

A skill your agent uses for Signet Dreaming development: inspect existing source, semantic-memory, retrieval, and inference architecture before changing it; prevent duplicate modules and ad-hoc…

Signet-AI/signetai

Benchmark Signet memory with MemoryBench: regression-check Dreaming and recall changes, compare models, diagnose score drops, and record results; NOT for the prompt-submit latency benchmark.

Signet-AI/signetai

Interactive interview to set up your Signet workspace (~5-10 minutes).

Signet-AI/signetai

Prune and route AGENTS.md trees for durable, high-signal context.

Signet-AI/signetai

Automatically benchmark your custom memory implementation against established systems like Supermemory.

Signet-AI/signetai

Maintain Signet's living ontology and memory substrate from transcripts, memory artifacts, source artifacts, notes, summaries, and imported records.

Signet-AI/signetai

Upgrade provider SDKs and refresh bundled model presets; NOT for unrelated provider architecture.

Signet-AI/signetai

Rewrite or create a public Signet docs page (web/docs) to the house template: verified facts, sequence diagrams, field lists, themed screenshots, hairline figure.

Signet-AI/signetai

Use Signet-specific recall and source search from Codex without confusing it with Codex native memory.

Signet-AI/signetai