AI R MCP server

<!-- mcp-name: io.github.pro-target/ai-r -->

ai-r

English | Русский | 中文 | 日本語 | Español

An agent reported "done." There's nothing to check it against.

ai-r reads the session history of any of the five coding agents and lets a fresh agent cold-check what git can't answer:

dangerous (and roll it back if it did), what it actually changed, what it cost;

• did it lie, did it break anything — did it keep its word, did it run anything

behind the edit.

• why it went that way — under which plan, with what intent, and whose hand was

Across our own corpus — 1600+ sessions of five agents in 20+ projects — that's

how we found 312 risky commands (rm -rf, curl|sh, git push --force): the

agent caught and rolled back two itself; the other 310 ran silently — git

won't show them.

git shows what made it into the code; ai-r shows whether you can trust how the agent got there. Read-only: no LLM calls, no network.

Quick example — an agent asks about history

The primary mode is MCP: an agent (Claude, Codex, …) calls ai-r directly and asks about history in plain language. For example — pull the plan the previous agent settled on, drafts discarded:

Show me the plan from the last session — final only, no intermediate revisions.
→ plan(session=…, kind="final")  →  get_body(id, shallow=true)

  plan:            "Migrate auth to JWT: 1) extract the check…"
  dropped_drafts:  2   ← two drafts the agent threw away along the way
  session:         a3f… (claude)

Fast edit attribution — one terminal command, across every agent at once:

ai-r find-file-edits auth.py --since 2026-06-01

2026-06-03  codex   auth.py  "add a refresh token"                 edit
2026-06-07  claude  auth.py  "extract the check into middleware"   edit

What hurts

the plan in one shape, the edits in another.

• "Done, I did X per plan Y" — with nothing to check it against: the agent keeps

did the other agent already try?"

• You switched agents mid-task and lost the thread. There's nowhere to ask "what

what request.

• An edit shows up in a file — and it's unclear which agent made it, and on

One cause: every agent writes its history its own way — Claude and Codex in JSONL, OpenCode in SQLite, Antigravity in "brain" directories, Pi in per-project JSONL. Five formats, five layouts — together they don't reconcile.

The promise

ai-r folds all five into one read-only interface. Point any agent — or a script, or yourself — at any session, no matter which tool recorded it. One query shape per agent; format differences are normalized inside the parsers.

Even with a single agent it works: you audit your own Claude history (or Codex…). The five formats are so your history doesn't break when you switch tools — not a requirement to have all five.

As a source for RAG

In an "LLM + external data source" setup (RAG), ai-r is the source — more precisely, a retrieval layer over agent sessions. For a query it returns not a slice of log but parsed entities: the plan, the intent, the authorship of an edit — with a reference to the body the agent can pull if it needs it.

Shortened. The full README is on GitHub.