Agentmetry
Free · Open source
SOC and DevSecOps teams
Selvedge
FreeOpen SourceSelf-Hosted
Six months after your AI agent rewrote the payments schema, git blame returns a commit message that says 'Update schema' and the session context is gone — Selvedge exists to make that moment not happen.
Similar tools
AgentmetryFreeAgentmetry is an open-source, local-only session recorder for AI coding agents — Cursor, Claude…
Comet AIFreemiumOpik connects the full loop: trace every step an agent takes, surface recurring silent errors…
Selfship.aiFreemiumThe observe-diagnose-fix-verify cycle runs on live traffic without you assigning tasks or…
TokenDamFreemiumThe tool runs entirely in the browser — nothing you paste leaves your machine — which means no…
Get This Tool
License: MIT Any use incl. commercial
Local-run terms: MIT license permits unrestricted use, modification, and distribution for any purpose, including commercial, provided the license and copyright notice are included.
Pricing
- Model
- Free
Summary
Selvedge is a local MCP server that AI coding agents (Claude Code, Cursor, Copilot) call as they work, logging the reasoning behind every change into a SQLite file that lives next to your code under .selvedge/. Queries are entity-scoped — you ask about users.email or deps/stripe, not line numbers — so the answer surfaces in the same terms you search in. The vendor describes zero telemetry, no accounts, and no external servers; everything stays on disk. The wall appears when your team needs cross-repo provenance or wants to pipe this data into an existing observability stack — Selvedge emits records but does not integrate with those systems out of the box.
Bottom line: Selvedge is the right call when one developer or one team needs to remember why their AI agent changed something three sprints ago; it is not the right call when you need that reasoning federated across multiple repositories or ingested by a compliance platform that expects a structured API.
Find your fit
Before you choose Selvedge
More options in LLM Observability. Compare pricing, platforms, and features side by side.
Comet AI
Freemium
Developers building GenAI apps and agents
Pros
- Reasoning is captured in the same context window that produced the change — not reconstructed from the diff afterward — which means the intent survives even when the original prompt, the developer who wrote it, and the model version are all gone.
- Entity-scoped queries (selvedge blame payments.amount, selvedge diff users --since 30d) let you ask about the things you actually search for rather than hunting through line-level history, so a schema audit that would take an afternoon takes a single command.
- Fully local storage in a SQLite file with no accounts, no telemetry, and no external servers, which means sensitive schema and API change history never leaves the machine — a hard requirement in compliance-heavy environments.
- Provider-agnostic MCP integration wires into Claude Code, Cursor, and Copilot through a single setup command, so teams already using any of those agents get provenance logging without changing their workflow.
- Full-text search across all logged events (selvedge search "stripe") and changeset grouping (selvedge changeset add-stripe-billing) mean you can reconstruct the full scope of a feature build after the fact, which is the audit trail that git log alone cannot provide.
Cons
- Selvedge has no API and no export integration — teams that need to push reasoning records into an existing compliance platform, a data warehouse, or a centralized observability system must write their own pipeline against the SQLite file, adding a maintenance surface that grows with audit requirements.
- The store is scoped to a single local project directory; teams running multi-repo codebases where an agent change in one repo depends on a change in another get no cross-repo provenance, and at that point teams managing compliance across repositories will move to a dedicated audit-log solution that operates at the organization level.
- Selvedge only captures what the agent explicitly logs through the MCP tool call — if an agent skips the log_change call, makes changes outside a supported tool, or the MCP connection drops mid-session, that change has no recorded reasoning and the gap is invisible in the history.
About
- Platforms
- Linux, macOS, Windows (via Python)
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- June 1, 2026
Best For
Who it's for
- Teams running long-term AI-coded codebases with turnover and long review cycles
- Solo developers using Claude Code on ongoing projects
- Compliance-heavy environments requiring audit trails for AI-generated changes
- Projects where schema, dependency, or API changes need documented rationale
What it does well
- Auditing why AI agents made schema changes or dependency updates in production systems
- Recovering intent months later when reviewing old AI-written features
- Compliance and governance—preserving decision reasoning for regulatory audits
- Solo developers working with Claude Code on side projects who want to remember past decisions
- Team code reviews to understand agent reasoning without hunting through session logs
Integrations
Compare Selvedge
Frequently Asked Questions
- Is Selvedge free?
- Selvedge offers a free option. Hosting, model usage, or optional services may have separate costs; check the pricing details and official terms.
- Is Selvedge open source?
- Yes. Selvedge is open source — the source repository is at https://github.com/masondelan/selvedge.
- Can I self-host Selvedge?
- Yes. Selvedge supports self-hosting on your own infrastructure.
- When was Selvedge released?
- Selvedge was first released in 2026.
- What platforms does Selvedge support?
- Selvedge is available on: Linux, macOS, Windows (via Python).
People also compared
Curated lists that include this category
AI agents write code fast and forget everything the moment the session closes. Selvedge intercepts that amnesia at the source: it runs as a local MCP server, and agents call its log_change tool during the session that produces each change — recording the reasoning in the same context window that generated the code, not inferred afterward from the diff. The result is a queryable SQLite store under .selvedge/ that answers questions like selvedge blame user_tier_v2 with the original prompt intent, the agent identity, and the commit hash — all tied together.
The differentiating design choice is entity-level attribution rather than line-level attribution. Where git blame tracks line ownership, Selvedge tracks the things engineers actually search for: a database column, an environment variable, an API route, a dependency. Prefix queries work across all of these, so selvedge diff users –since 30d returns every agent-logged change to anything in the users namespace over a thirty-day window. That granularity is what makes it useful for schema audits and dependency change reviews, not just curiosity.
Selvedge fits between git (which records what changed) and PR review tools (which assess quality at merge time) — the vendor describes it explicitly as a provenance-as-first-class-citizen layer. It does not replace agent observability tools that trace LLM calls, and it does not replicate code-host AI features. Where it breaks down: the store is local and per-project. Teams that need reasoning records federated across repositories, or that need to push compliance artifacts into an external system via API, will find no native integration path — Selvedge has no API surface of its own.
Setup runs three commands: pip install selvedge, cd your-project, selvedge setup. The setup step detects which AI tools are present on the machine and writes Selvedge into each one’s config. A selvedge watch command live-tails events as an agent works. Every modified file gets a .bak written before any change reaches disk. Dependencies are limited to MCP, Click, and Rich — the vendor states no additional dependencies and no telemetry.
Contribute
- Work on Selvedge? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.