// readme

Shared local memory across Claude Code, Codex, Cursor, Kimi, Grok, and OpenCode.
Session ten does not re-learn what session one already ruled out.

The problem

New coding-agent sessions start blank. Context gets re-pasted across Claude Code, Codex, and Grok. The tenth thread is not smarter than the first — just more expensive.

What Solenta remembers

A local memory server is auto-injected into every session. SQLite on disk, FTS + vector search, HTTP + MCP, localhost-only, bearer-token gated. No per-agent wiring.

Claude Code · thread 1
  Ruled out a rewrite of auth. Cookie session stays.
  Refresh lives in src/lib/auth.ts.

Codex · thread 3
  The 401 retry is in src/lib/api.ts.
  Moving it breaks the refresh path.

Grok · thread 6
  Starts knowing both. Adds the expiry skew
  and leaves the rest alone.
  • Hypothesis ledger — the next thread inherits what the last one already ruled out.
  • Provenance and trust score — every entry tracks which agent wrote it and how reliable that agent has been.
  • File:line / thread / commit citations — before a fact is injected, its file citations are checked against the current worktree; contradicted…
↑ The Undervalued Score +

How much a project earns versus how much attention it actually gets. Above 50 means the work is outrunning its audience. Recomputed nightly from commit velocity, contributor effort, issue resolution, fork utility, release cadence, and project maturity — divided by a logarithmic reach factor.

score  = signal / reach

signal = 0.25·commit_velocity   // commits in last 90 days (cap 30)
       + 0.20·contributor_work  // unique authors × velocity (cap 100)
       + 0.20·issue_resolution  // closed ÷ total issues
       + 0.20·fork_ratio        // forks ÷ stars (proxy for real usage)
       + 0.10·release_cadence   // releases in 90 days (cap 3)
       + age_bonus              // +0 to +0.30 after 6 months
       + homepage_bonus         // +0.05 if homepage is set

reach  = log₁₀(stars + watchers + 10)█
♥ The Health Score +

Is the project alive and maintained right now? A 0–100 pulse recomputed nightly from commit recency, rhythm, how fast issues close, and how quickly PRs get merged.

health = 0.35·recency       // days since last commit (90d decay)
       + 0.25·cadence       // commit rhythm consistency
       + 0.20·issue_health  // closed ÷ total issues
       + 0.20·pr_health     // merged ÷ total PRs█
◷ Health bands +

The colour and label on every card come straight from the health score.

Healthy   80 – 100   active, responsive, regular releases
Stable    60 – 79    maintained, steady, no alarms
Quiet     40 – 59    slowing down — watch this one
At Risk    0 – 39    going dark · candidate for rescue█
// Tags — what each label means +

Tags are independent behavioral signals computed nightly. A project can hold multiple at once. They drive the home page sections.

solo_builder      one person holds > 80% of commits (last 180d)
needs_contributors has open "help wanted" or "good first issue" labels
hidden_gem        < 100 stars · active in last 3 months · documented
legacy_hero       repo > 5 years old · committed this year
fork_magnet       forks/stars > 0.5 · used as template or dependency
release_machine   5+ releases in the last 90 days
under_pressure    > 10 open issues · ≤ 2 contributors · health ≥ 60
community_watch   watchers > stars · devs tracking before the public
community_hub     GitHub Discussions enabled · > 20 discussions
funded            maintainer has active funding channel█
★ Why rank against stars at all? +

Stars are an outcome, not effort. A project with 8 stars and daily commits is doing more interesting work than one coasting on 8k. We measure the building, then divide by the attention already received — so the genuinely undervalued rise to the top.

// stars   = lagging indicator
// commits = leading indicator
// we rank by the leading one█