Pre-load + pre-embed each target scholar's corpus into a Mira trial bundle, then ship that bundle to them as the working demo. A scholar trying Mira on their own archive will give up before the embedder finishes. A scholar opening Mira and seeing their own life's work already queryable is a postdoc pitch.
chroma_data/, mira_library.db, and the source PDFs into a
portable trial-bundle folder.project_postdoc_outreach_preembedded_corpora.md
·
Bee CSV: ~\Documents\thunderbird-sync\events.csv
| Name | Password | Role | Alpha | Verified | Enabled | Last Login | Usage | Actions | |
|---|---|---|---|---|---|---|---|---|---|
| Loading... | |||||||||
Send an invite link instead of typing the user's password. The user opens the link, enters their own password, and the link is single-use with a 72-hour expiry.
Send this URL to the user out-of-band (email, Signal, in person). It can only be used once and expires automatically.
| Role | Alpha | Sent | Expires | Actions | |
|---|---|---|---|---|---|
| Loading... | |||||
| Date | Requests | Input Tokens | Output Tokens | Cost |
|---|---|---|---|---|
| Loading... | ||||
| Model | Requests | Input Tokens | Output Tokens | Cost |
|---|---|---|---|---|
| Loading... | ||||
Create shared-key bundles (e.g. "Alpha testers") and grant them to users so collaborators can use Mira's LLM features without supplying their own API keys. Users' personal keys always take precedence over team keys when both are available.
| Bundle | Requests | Input Tokens | Output Tokens | Cost (USD) |
|---|---|---|---|---|
| No usage data yet. | ||||
Cross-user log of pipeline-stage failures where automated rescue did not succeed, with the root cause and the fix proposed by the self-healing subagent. Proposals are logged only — none are applied automatically.
| Time | File | User | Stage | Failure | Root Cause | Proposed Fix | Model |
|---|---|---|---|---|---|---|---|
| Loading... | |||||||
Tail of the structured server log (and the launcher log). Newest entries first. Use this instead of a shell — no SSH needed to see why the server crashed.
Per-tier metadata-extraction success rate across all library files. Each row shows how many files were processed by that tier, and what fraction produced bibliographic data (success), found no match, had no input to query, or errored. Use this to find tiers that routinely cost time without producing results — candidates for later cost-cutting.
| Tier | Tried | Success | No match | No input | Error | Success % |
|---|---|---|---|---|---|---|
| Loading… | ||||||
Run intake-parse + GROBID against a specific library file and inspect the resulting tier ledger, persisted metadata, and raw artifacts. GROBID fulltext can take 30-180 seconds on large PDFs.
| file_id | stamp | report | actions |
|---|---|---|---|
| Loading… | |||
Subscribes to the live pipeline event stream. Run a file (Acquisitions / Library) and watch which stages and sub-steps actually fire, when, how long they take, and exactly where the chain stops. States are derived directly from events — not fired, running, ok, failed, and not reached are distinct, so a dark stage is never ambiguous. Read-only observer; it does not alter the existing progress pills.
No files seen yet on this connection. Run a file to populate the trace.