Estran vs Selvedge

Estran 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.

Estran

Estran automates the analytical heavy lifting of flood risk assessment — vulnerability mapping, multicriteria scoring, adaptation scenario comparison — so municipalities and engineering firms can move from raw data to defensible recommendations without commissioning a full hydrological study for every scenario. The vendor states that agentic AI handles a substantial portion of the hydrological analysis, with human judgment retained for the roughly 20% of decisions that require discretionary calls. That division matters: the platform is not a replacement for a licensed engineer, it's a capacity multiplier. Where it breaks is at the edges of the regulatory model — teams working on cross-provincial projects or operating outside Quebec's 2026 framework will find the tool's specificity becomes a constraint rather than an advantage.

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	Estran	Selvedge
Pricing	Paid	Free
Free trial	No	No
Open source	No	Yes
Has API	No	No
Self-hosted option	No	Yes
Platforms	Web	Linux, macOS, Windows (via Python)
Released	—	2026-05
Pros	Agentic AI automates a substantial portion of hydrological analysis per vendor documentation, so engineering firms can take on more flood planning mandates without proportional headcount increases — the bottleneck shifts from analyst hours to senior review time. Multicriteria comparison of adaptation strategies (relocation, retrofitting, nature-based solutions) is built into the core workflow, which means councils get scenario analysis they can defend to regulators rather than a single-option recommendation that reopens debate. Territorial vulnerability mapping updates dynamically as demolitions, adaptations, and construction changes are recorded, so a municipality running a multi-year compliance program does not have to commission a fresh baseline study every time the zone changes. The platform is explicitly scoped to Quebec's 2026 regulatory framework, which means the output structure matches what provincial compliance requires — teams working toward that deadline are not adapting a generic tool to fit a specific filing requirement. Positioning as a lower-cost alternative to full hydrological contracts means smaller municipalities with limited capital budgets can produce defensible flood adaptation strategies without the procurement overhead of a $500k+ consulting engagement.	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	The platform's tight scoping to Quebec flood regulation means any project that crosses provincial lines or operates under a different regulatory standard hits a wall immediately — there is no documented configurability for other jurisdictions, and teams in those situations will need a different tool from day one. No API is available per the tool data, which means Estran cannot feed outputs into an existing GIS pipeline, municipal data warehouse, or engineering firm's project management stack without manual export steps — at sufficient project volume, that export friction becomes a recurring labor cost. Pricing is custom and not published, which introduces procurement delay for public-sector clients who cannot begin a budget approval process without a quote — municipalities operating on fixed annual planning cycles may find the negotiation timeline conflicts with their 2026 preparation schedule. Human oversight is retained for the discretionary 20% of analysis, per vendor documentation, which is appropriate — but it also means the platform cannot fully replace a licensed engineer on the project. Firms expecting to remove professional oversight from the billing equation entirely will need to restructure their expectation before the contract is signed.	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

Estran is paid while Selvedge is free; Selvedge is open source. Choose based on which difference matters most for your workflow.

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