Decisiontrail

io.github.CloudCorpRecordsPublished by GitHub account CloudCorpRecordsv0.1.0Updated Nov 7, 2026

Local decision memory for coding agents: record decisions with limits, search precedents, supersede.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Local decision memory for coding agents: record decisions with their constraints, search precedents, and supersede old calls.

What you can do
  • Record decisions: commit a plain decision with constraints and domain, or log a validated decision record from constraints, evidence and an answer.
  • Find precedents: get short pointers to prior decisions before deciding, or search validated records for full precedents.
  • Read and revise: expand a decision ID into its full record, or supersede an older decision with a linked successor.
  • Survey the store: get active decision threads by domain, namespace and counts, a competency profile, and duplicate or stale candidates.
When to use it
Useful when a coding agent makes recurring architectural or tooling calls (database, cache, release cadence) and you want later sessions to find the earlier reasoning instead of re-deciding, with explicit revisions rather than silent edits.
Requirements
Runs locally via npx or the Docker image; no account, login or network access. Decisions are stored in one JSON file at the DECISIONTRAIL_DB path, defaulting to ~/.decisiontrail/decisions.json. DECISIONTRAIL_AGENT and DECISIONTRAIL_PROJECT name the namespace and default to local. With Docker, mount a volume over the store directory to persist decisions.
Before you install
The server writes to a local JSON file: commits, validated records and supersede operations change stored data, and supersede marks the old record superseded. The store holds your project's decision history in plain text, so treat the file as sensitive. The connected-mode team tools of the original server are not included, so there is no shared workspace.

Installation

In SourceWeft

  1. Open Decisiontrail in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

decisiontrail

decisiontrail is a local decision memory for coding agents. When an agent makes a call — which database, which cache, which release cadence — decisiontrail records the decision together with the limits it was made under, so a later session can find the precedent instead of re-deciding from scratch, and can revise it explicitly when the call changes.

Everything is local: decisions live in one JSON file on your machine. There is no account, no login, and no network access. Records can be plain commits or validated decision records (constraints, evidence and an answer); validated records are the ones precedent search draws on. Old decisions are never edited in place — a revision creates a new record and marks the old one superseded, linked in both directions.

This package is a clean-room rebuild of the local surface of the "elen" MCP server (10 of its 12 tools). The original's two connected-mode beta tools, elen_incoming and elen_team_search, need a hosted workspace, a login and an API key, and are not included.

Install

bash
npx @reneturcios/decisiontrail elen_status

Or run the container image:

bash
docker run -i ghcr.io/cloudcorprecords/decisiontrail

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead. If you run the container, mount a volume over the store directory if you want decisions to persist.

Where decisions live

  • Store path: the DECISIONTRAIL_DB environment variable, or ~/.decisiontrail/decisions.json by default.
  • The file is a single JSON document. A missing file starts empty; writes are atomic (temp file, then rename), so a crash mid-write cannot truncate the store.
  • DECISIONTRAIL_AGENT and DECISIONTRAIL_PROJECT name the namespace reported by elen_status; both default to local.

Decision IDs are sequential: d-1, d-2, … in creation order.

CLI

One bin serves both faces. Each tool is a subcommand taking a single JSON argument (optional for the no-argument tools); results print as JSON.

bash
# Check the namespace before committingdecisiontrail elen_status
# Commit a decision with its limitsdecisiontrail elen_commit '{"text":"Use Postgres for sessions","constraints":["must be durable"],"domain":"storage"}'
# Record a validated decisiondecisiontrail elen_log_decision '{"constraints":["latency under 100ms"],"evidence":["benchmark run 42"],"answer":"Adopt the in-process cache","domain":"performance"}'
# Before a new decision, ask for pointers; then search validated precedentsdecisiontrail elen_suggest '{"query":"session storage"}'decisiontrail elen_search_precedents '{"query":"session storage"}'
# Read one record in full, revise one, survey the storedecisiontrail elen_expand '{"id":"d-1"}'decisiontrail elen_supersede '{"id":"d-1","text":"Use Redis for sessions with Postgres fallback"}'decisiontrail elen_get_contextdecisiontrail elen_get_competencydecisiontrail elen_consolidate
decisiontrail --version

Exit codes: 0 on success, 1 for a domain error (for example an unknown decision ID — the error names the ID), 2 for usage errors and invalid arguments.

MCP server

bash
npx -y @reneturcios/decisiontrail mcp

MCP client configuration:

json
{  "mcpServers": {    "decisiontrail": {      "command": "npx",      "args": ["-y", "@reneturcios/decisiontrail", "mcp"]    }  }}

Tools

ToolInputWhat it returns
elen_committext (required), constraints (string array), domainThe new unvalidated decision record.
elen_log_decisionconstraints, evidence, answer (all required), text, domainA validated decision record built from those inputs.
elen_expandid (required)The full record for that decision ID.
elen_suggestquery (required), limit (default 5)Short pointers (id, first 120 chars of text, domain, validated, status) to prior decisions matching the query, best match first. Considers all records.
elen_search_precedentsquery (required), limit (default 5)Full records matching the query, validated records only.
elen_supersedeid, text (both required), constraints, domainThe new successor record; the old record is marked superseded and the two are linked both ways.
elen_get_context—Active decision threads grouped by domain, with per-domain counts and the latest text, plus totals.
elen_status—Agent, project, database path, and counts (total / active / superseded / validated).
elen_get_competency—Validated-record counts per domain and the validated share (coverage) of all records, derived from validated history only.
elen_consolidate—Duplicate pairs (same domain, token Jaccard at least 0.6), the clusters they form, and stale candidates (active records older than 90 days). Changes nothing.

How matching works

elen_suggest and elen_search_precedents rank by case-insensitive token overlap between the query and a record's text plus constraints: the score is the number of distinct query tokens present. Records with no overlap are omitted; ties are broken by recency, newest first.

A record counts as validated only when it was created with elen_log_decision. A committed decision that is later superseded keeps its history: supersedes / superseded_by link the chain and the old record's status becomes superseded.

Development

bash
npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, temp dirs, no networknpm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

Source: README.md at commit 6169cda

Tools

10

elen_commit

Commits a new decision to the graph, with its constraints as a plain-text list.

Parameterstextrequireddomainconstraints

elen_log_decision

Creates a validated Decision Record from constraints, evidence and an answer.

Parameterstextanswerrequireddomainevidencerequiredconstraintsrequired

elen_expand

Expands a decision ID into its full constraints and text.

Parametersidrequired

elen_suggest

Retrieves short pointers to prior decisions before you make a new one.

Parameterslimitqueryrequired

elen_search_precedents

Searches validated decisions for precedents.

Parameterslimitqueryrequired

elen_supersede

Revises an older decision and marks it superseded by a new one.

Parametersidrequiredtextrequireddomainconstraints

elen_get_context

Gives an overview of active decision threads grouped by domain, for the start of a session.

Takes no parameters.

elen_status

Returns the agent, project, database path and counts, to check the namespace before committing.

Takes no parameters.

elen_get_competency

Shows the competency profile for this agent, built from its validated decision history.

Takes no parameters.

elen_consolidate

Suggests clusters and duplicate or stale candidates without changing the graph.

Takes no parameters.

Version history

1
  1. v0.1.0LatestNov 4, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts