
Recordant
io.github.recordantPublished by GitHub account recordantv0.2.2Updated Nov 3, 2026
Patent-pending diagnostic + decisions-ledger engine with operator briefs and an MCP console.
Overview
Licensed diagnostic and decisions-ledger engine that scans a target repo, changelog and logs, then exposes briefs and open diagnoses through a chat MCP console.
- What you can do
- Read the latest delta brief and current status snapshot for a scanned target
- Review open diagnoses with age, recurrence and evidence, plus digests of accepted risks, shipped fixes and deadlines
- Acknowledge, accept-risk or resolve diagnoses, with resolutions audited against the changelog
- Run periodic scans that produce operator briefs, snapshots and an optional decisions ledger in a configured output directory
- When to use it
- For teams that want an assistant to answer questions about what changed, what looks broken and what was fixed in a software system, and to track diagnoses and accepted risks over time. It suits ongoing operational review of a repo plus its logs rather than one-off code questions.
- Requirements
- Runs locally over stdio as the recordant-mcp command from the recordant PyPI package (uvx or pip), with a recordant.toml config naming repo_root, changelog_path, log_globs and the LLM provider settings. A required RECORDANT_LICENSE_KEY is verified against a license service at startup, and a bring-your-own LLM API key is supplied via the environment variable named in api_key_env. Network access is needed for license verification and LLM calls.
Installation
In SourceWeft
- Open Recordant in the dashboard and add it to a workspace.
- 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
Recordant
Recordant is a patent-pending diagnostic + decisions-ledger engine for any host software system. Point it at a target's repo, changelog, and logs, and it runs a periodic scan that produces an operator brief: what changed, what looks broken, what was fixed, and a prioritized diagnosis list — plus a chat-native MCP console over the same data.
Bring your own LLM (Anthropic, OpenAI, or Gemini — your key, your usage, your bill). Recordant makes no provider assumption.
15-minute install and first brief
-
Install the package and your LLM provider's SDK (only the one you use):
-
Copy
recordant.example.tomltorecordant.tomland set:repo_root— the target repo to diagnosechangelog_path— usuallyCHANGELOG.md(falls back togit logif absent)log_globs— which log files to health-scan[llm]— your provider, model, andapi_key_env(the name of the environment variable holding your key — never the key itself)
-
Export your key and run one cycle:
The brief path prints to stdout. The brief, snapshot, and (optional) decisions ledger are written under your configured
output_dir. -
Schedule it (cron / systemd timer / your own scheduler) at the
schedule_secondscadence in your config.
That's the whole loop. See ENGINE.md for the adapter architecture, config
reference, and known limitations.
MCP console
Recordant also runs as an MCP server exposing 7 tools over stdio, for use from a chat-native MCP client:
Token-auth is on by default — there is no anonymous mode. The server
requires a valid RECORDANT_LICENSE_KEY and verifies it against the license
service at startup before registering a single tool; it will not run
unlicensed, even briefly. A short offline-grace window covers a transient
network failure to the license service, but an explicitly invalid or expired
key is refused immediately.
Add it to your MCP client's config (Claude Desktop, Claude Code, etc.):
Licensing and pricing
Recordant is licensed software, not open source (see LICENSE). Get a key
and see current pricing at
https://mentorsentinel.ai/markets-ai-governance.html.
Docker
Recordant ships as a compiled image -- there is no engine source to build
from, so docker build is not part of a customer workflow. Pull the
licensed image (published per BUILD-RELEASE.md) and run it:
The image is signed (cosign) and ships with an SBOM (syft) so you can audit
what it does -- dependencies, egress -- without needing readable engine
source; see BUILD-RELEASE.md for verification commands.
See docker-compose.example.yml for a compose-based setup, including the
MCP console service.
Support
Found a bug or have a feature request? Open an issue — see
.github/ISSUE_TEMPLATE/. For licensing or account questions, use the
pricing page above.
Patents
Recordant's inference loop and decisions-ledger lifecycle are patent-pending (U.S. application numbers available on request). "Patent-pending" reflects filed, unexamined provisional applications — no patent has issued.
Source: README.md at commit d8adef8
Tools
0Version history
1- v0.2.2LatestSep 16, 2026
Score
40% 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
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- 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 listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.