V0.1.1 — RECURSIVE REASONING

The Whole
in Parts.

Recursive language model reasoning for documents. Iterate with search, code, and think tools. Converge on answers with provenance.

GET STARTED VIEW ON GITHUB
LOAD

Context stored in REPL as variable ctx

→
EXPLORE

Search, peek, chunk, execute Python

→
CITE

Evidence auto-accumulates with provenance

→
CONVERGE

Evaluate progress, finalize with citations

↻ THE RECURSIVE LOOP
MCP SERVER

Provenance
Tracking.

Every search, every citation, every piece of evidence is automatically logged. When you finalize, you get a complete audit trail of how you reached your answer.

  • <> exec_python — Run code against context
  • ⌕ search_context — Regex search with evidence logging
  • ✓ cite() — Tag findings with notes
  • ◉ evaluate_progress — Track convergence

EVIDENCE TRAIL

⌕ [search] pattern: "liability" lines 42-58
✓ [manual] note: "key exclusion clause"
⌕ [search] pattern: "indemnif" lines 112-130
✓ [manual] note: "carve-out for negligence"

CONFIDENCE: HIGH (0.92)

→ Ready to finalize with 4 citations

"What my eyes beheld was simultaneous, but what I shall now write down will be successive, because language is successive."

— Jorge Luis Borges, "The Aleph" (1945)