Bitloops vs Selvedge

Bitloops and Selvedge are both inference engines & infra tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Bitloops

Bitloops runs as a local CLI that builds a semantic model of your codebase and captures AI interactions — prompts, reasoning, decisions — then links them to the Git commits they produced. The vendor describes it as an intelligence layer sitting between your repository and your agents, so Claude Code, Cursor, Codex, or Copilot pull structured context instead of crawling raw source. Everything stays local: no cloud proxy, no data leaving your environment. The constraint enforcement pillar is listed as coming soon, which means teams that need automated rule enforcement on generated code are buying a roadmap item, not a shipping feature. Early-stage tooling with real architectural intent, but the feature set reflects a pre-seed trajectory.

Selvedge

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.

Attribute	Bitloops	Selvedge
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	CLI, local daemon	Linux, macOS, Windows (via Python)
Released	2021	2026-05
Pros	Local-first architecture with data stored directly in your repository, so no code or reasoning leaves your environment — which means teams with air-gapped or compliance-sensitive codebases can adopt it without a security review of a cloud dependency. Agent-agnostic design supports Claude Code, Cursor, Codex, Gemini, Copilot, and OpenCode from a single install, so switching or running multiple agents in parallel does not fragment the context model. Commit-aware session linking ties every AI interaction to the Git history it produced, which means you can trace a line of code back to the prompt that generated it and the alternatives that were rejected — the audit trail that AI-generated code has been missing. Context accumulates across sessions instead of resetting, so agents on your team's second or fifth project with this codebase are not starting from the same blank slate as day one. Runs fully offline after install, which means a dropped connection or API outage does not take your context infrastructure down with it.	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	Constraint enforcement — the feature that applies architectural rules automatically to AI-generated code — is listed as coming soon and is not a shipping capability. Teams that need policy enforcement on generated output today will add a separate tool, then face the maintenance cost of two systems once Bitloops ships its own version. No API surface is available, so teams that want to integrate Bitloops context retrieval into custom CI pipelines, code review automation, or internal tooling cannot do so programmatically — the CLI is the only interface, and teams that hit this wall typically reach for a solution they can script against. The semantic model and captured reasoning are stored in the repository, which means on a large monorepo the storage and indexing overhead is an open question the vendor page does not address — teams managing repositories at that scale should validate this before committing the tooling to production.	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.

Bottom line

Bitloops and Selvedge are closely matched on pricing model, openness, and API availability — pick by feature set and platform support in the table above.

Comparison data is sourced and verified by the AIDiveForge data pipeline. AIDiveForge is editorially independent.