Selvedge

Long-term memory for AI-coded codebases. A git blame for AI agents — but for the why, not just which line which model touched. Captured live, by the agent, as the change happens.

Selvedge is a local MCP server. AI coding agents (Claude Code, Cursor, Copilot) call it as they work to log structured change events with reasoning. Your data stays in a SQLite file under .selvedge/ next to your code.

Six months ago, your AI agent added a column called user_tier_v2. You don't know why. git blame points to a commit from claude-code with a generated message that says "Update schema." The session that made the change is long gone — and so is the prompt that produced it.

With Selvedge, you run this instead:

$ selvedge blame user_tier_v2

  user_tier_v2
  Changed     2025-10-14 09:31:02
  Agent       claude-code
  Commit      3e7a991
  Reasoning   User asked to add a grandfathering flag for legacy free-tier
              users during the pricing migration. Stores the original tier
              so we can backfill discounts without touching billing history.

That reasoning was captured by the agent in the moment — written into Selvedge from the same context that produced the change. Not inferred from the diff afterward by a second LLM. Not a hand-typed commit message.

Who Selvedge is for

Selvedge has two audiences. Same tool, same pip install, same SQLite file under .selvedge/. Different scale of pain.

Teams running long-term, AI-coded codebases. When the project is big enough that you (or someone else) will touch it again in six months, twelve months, three years — but most of it was written by an agent whose context evaporated the day each PR shipped. git blame tells you what changed. Selvedge tells you why — even after the agent session, the prompt template, the developer who asked for it, and the model version are all long gone. This is the original use case: production codebases, schema decisions, migrations, dependency changes that need an audit trail that survives turnover.

Solo developers using Claude Code on everyday projects. Side projects, weekend builds, the small internal tool you keep poking at. You don't need enterprise governance — you just need to remember why you (or your agent) did the thing you did yesterday, last week, last sprint. Run selvedge init once. Add four lines to your CLAUDE.md. From then on, selvedge blame is muscle memory — a way to talk to your past self when your past self was an LLM.

If you've ever come back to your own AI-built project and thought "what was this for again?", Selvedge is the missing piece.

The problem

Human-written code leaks intent everywhere — commit messages, PR descriptions, inline comments, the Slack thread that preceded it. AI-written code doesn't. The agent has perfect clarity about why it made each decision, but that context lives in the prompt and evaporates when the conversation ends.

Six months later, your team is debugging a schema decision with no trail. git blame tells you what changed and when. It can't tell you why.

Selvedge captures the why — live, by the agent itself, as the change is made. The diff is git's job. The why is Selvedge's.

What's new in v0.3.9

Agent Trace export — Selvedge is a compatible producer. selvedge export --format agent-trace emits Agent Trace v0.1.0 records — the open AI code-attribution wire format from Cursor + Cognition AI — so your captured history travels to any tool that reads the standard. Selvedge's reasoning and entity-level provenance ride along in each record's metadata under the dev.selvedge namespace. Drop-in upgrade for anyone on 0.3.8.

selvedge export --format agent-trace -o trace.json            # one record per event
selvedge export --format agent-trace --ndjson -o trace.ndjson # stream, one per line
selvedge export --format agent-trace --collapse-by-session    # merge a session into one record
selvedge import trace.json --format agent-trace               # round-trip back in

It's opt-in and additive — nothing about the native model, the 8 MCP tools, or local SQLite changes. Entity-level events (a column, an env var, a dependency) have no line range, so Selvedge marks them metadata.dev.selvedge.range_unknown: true rather than fabricating one — an honest fidelity signal. This was planned for v0.4.0; only the exporter moved forward (Postgres + the tool rename remain the v0.4.0 markers; HTTP + auth ships in v0.4.1). Full mapping in docs/agent-trace-interop.md.

What's new in v0.3.8

Active memory v1 (date-based). Selvedge's append-only log learns to know when its own data is stale. A decision can now carry a revisit date, and the new stale_decisions tool surfaces decisions that have aged out — but only the ones whose entity is still in active use, so an old-but-correct decision nobody touches never nags. Drop-in upgrade for anyone on 0.3.7. This brings the MCP surface to 8 tools.

revisit_after + stale_decisions — decisions with an expiry date

Set revisit_after on an architectural log_change — an ISO date or a relative offset like 90d:

log_change({
  "entity_path": "deps/stripe", "change_type": "add", "entity_type": "dependency",
  "reasoning": "Pinned Stripe SDK to v11 for the billing launch.",
  "revisit_after": "180d"   // revisit this pin in ~6 months
})

Later, stale_decisions returns the dated decisions that have come due — and filters out pure age:

stale_decisions({})
// → only decisions past their revisit date whose entity is STILL in use:
[
  {
    "entity_path": "deps/stripe", "change_type": "add",
    "reasoning": "Pinned Stripe SDK to v11 for the billing launch.",
    "revisit_due": "2026-...Z", "days_overdue": 12,
    "active_use_signals": ["queried"],
    "stale_reason": "past its revisit date and still active — the entity was queried (blame/diff/prior_attempts) after the decision."
  }
]

Pure age never surfaces. A decision only comes back if the entity is still live — recently queried (blame / diff / prior_attempts) or its changeset kept moving. That's the noise defense: a dated decision nobody has touched won't nag. Templated and deterministic — no LLM, ever. The pattern-based half (expires_when grammar, explicit reject/revert change types) lands in v0.3.11; the v0.3.8 migration adds the expires_when column now so that's a no-migration release.

CLI parity for the wedge + CLI-awareness

selvedge prior-attempts <entity> lands — the v0.3.7 prior_attempts wedge was the only MCP tool without a CLI command. It's a thin presenter over the same store, so --json emits the identical list the tool returns. New selvedge stale mirrors stale_decisions (with --json for cron / Slack jobs). And the canonical agent-instructions block now names the CLI equivalents alongside the MCP tools, so a shell-having agent is never blocked when the MCP server isn't loaded. Selvedge stays MCP-first; the CLI is the additive second path.

See CHANGELOG.md for the full list, the one-time migration-v3 note (metadata-only ADD COLUMN, fast even on multi-million-event DBs), and the called-out test-budget overage from the bundled CLI + agent-block work.

Where Selvedge fits

AI agents call Selvedge as they work. Selvedge captures the why into a durable, queryable store and emits it back out — as Agent Trace records for cross-tool readers, as observability metadata that links into Sentry/Datadog stack traces, and as compliance artifacts for SOC 2 and EU AI Act audits.

Selvedge does not replace git (line-level what/when), PR review tools (review-time quality), agent observability (LLM call traces), or general-purpose code-host AI features. It sits between them — the provenance-as-first-class-citizen layer that everything else references.

How Selvedge compares

There's a fast-growing "git blame for AI agents" category. Here's where Selvedge fits — and where it deliberately doesn't.

Why "captured live" matters. AgentDiff and Origin generate reasoning after the change is made, by feeding the diff back to a second LLM call. Selvedge's reasoning is the agent's own intent, written from the same context window that produced the change — no inference, no hallucinated explanations, and an empty reasoning field is itself a useful signal (the agent didn't have one).

Why "entity-level" matters. Most tools attribute lines. Selvedge attributes things you actually search for: users.email, env/STRIPE_SECRET_KEY, api/v1/checkout, deps/stripe. The first question after git blame is usually "what's the history of this column", not "what's the history of lines 40–48 of users.py".

Why "changesets" matter. A Stripe billing rollout touches the users table, two new env vars, three new API routes, one dependency, and four functions across the codebase. Tag every event with changeset:add-stripe-billing and you can pull the entire scope back later — even if the original PR was broken into eight smaller ones over a month.

Selvedge ↔ Agent Trace. Agent Trace (Cursor + Cognition AI, RFC Jan 2026, backed by Cloudflare, Vercel, Google Jules, Amp, OpenCode, and git-ai) is an emerging open standard for AI code attribution traces. Selvedge isn't a competitor to it — it's a compatible producer. As of v0.3.9, selvedge export --format agent-trace emits Agent Trace v0.1.0 records (and selvedge import --format agent-trace reads them back); the mapping

…