Skip to content

Selvedge vs. Origin

Origin (opsworks-co/origin-cli) captures automatically — agent lifecycle hooks record prompt receipts live, per turn, anchored to commits in git notes. Selvedge captures the agent’s stated reasoning through MCP. The trade is coverage vs. content: receipts everywhere, or testimony where it matters.

SelvedgeOrigin
Reasoning sourceCaptured live, by the agent in the same context that produced the changePrompt receipts, captured live per turn — prompt, diff, tokens; no stated rationale
GranularityEntity — DB column, table, env var, dep, API route, functionLine
MechanismMCP server — the agent calls it as work happensAgent lifecycle hooks + global git post-commit hook
GroupingChangesets — named feature/task slugs across many entitiesBranch-level trail view; no entity-spanning changesets
Prior attemptsYesprior_attempts surfaces tried-and-rejected pathsNone — rework flags reverted AI code post-hoc, without rationale
StorageSQLite, zero depsGit notes (refs/notes/origin) + a sessions branch; optional cloud sync
  • Receipts vs. testimony. Origin records what the prompt and the diff were — automatically, across a dozen-plus agents. Selvedge records what the agent said it was doing and why, from the context that had the reasoning. A receipt can tell you a change followed a prompt; it can’t tell you which alternatives were weighed and killed.
  • Rejected paths. Origin’s rework command detects AI code that was later reverted or heavily modified — a post-hoc diff heuristic yielding a rework-rate report, with no rationale attached and no queryable record of why the approach died. Selvedge’s prior_attempts returns the tried → reverted → re-opened trail with the stated reason at each step.
  • Entity-level granularity. Selvedge’s unit is the column / env var / route / dependency / function, with prefix queries — not lines that drift as the file evolves.
  • Read path for the agent. prior_attempts, blame, diff, and stale_decisions are callable by the agent mid-task, and the SessionStart digest pushes standing verdicts into new sessions. Origin’s queries (origin why, origin blame, session search) are developer-facing; nothing pushes a prior verdict back into the agent’s context.

If you want automatic, zero-cooperation capture across a dozen-plus agents — prompts, diffs, and token costs riding along in git notes with optional cloud sync — Origin’s coverage and near-zero adoption friction beat an MCP-cooperation model. Reach for Selvedge when what you need back is the reasoning and the rejected paths, not the receipts.