Toji

Toji is a Pi extension workspace with two packages:

• toji-mem: local code memory, search, graph traversal, and benchmarks
• toji-comms: AI-to-AI communication bridge for Pi agents

What toji-mem does

toji-mem indexes a repository into SQLite and answers common agent questions:

• where is this symbol?
• what file should I read?
• what related files/symbols are nearby?
• what might be affected if I change this symbol?

It uses:

• SQLite FTS5 for fuzzy search over files, symbols, docstrings, and paths
• B-tree indexes for exact file and symbol lookups
• Tree-sitter parsers for symbols, imports, and calls
• graph edges for blast-radius and related-file traversal

What toji-comms does

toji-comms lets the active Pi model send a structured message to a peer model through MCP/mmx, then stores the discussion in SQLite.

It provides:

• toji_comms_send for AI-authored peer messages
• toji_plan_run as a compatibility alias for plan workflows
• thread history in ~/.pi/agent/toji-comms/toji-comms.sqlite
• commands for model, mode, thread, and plan control

Install from Pi

After publishing to npm, install Toji like this:

pi install npm:@mr-jones123/toji

Try it for one Pi run without installing:

pi -e npm:@mr-jones123/toji

Local setup

bun install

Use with Pi

If installed with pi install, start Pi normally and both extensions are discovered.

For local development, start Pi with one extension loaded:

pi -e ./packages/toji-mem/src/index.ts
pi -e ./packages/toji-comms/src/index.ts

toji-mem commands

/toji-index .
/toji-query indexProject
/toji-overview .
/toji-graph index project
/toji-blast indexProject
/toji-bench .

| command | purpose | |---|---| | /toji-index [path] | index a project into Toji memory | | /toji-query <query> | search indexed files, symbols, and standards | | /toji-overview [path] | show compact project overview, expandable in Pi | | /toji-graph <intent> | find related files/symbols from a natural-language intent | | /toji-blast <symbol> | traverse likely impact radius for a symbol | | /toji-bench [path] | run the operational benchmark from inside Pi |

toji-comms commands

/toji-comms <message>
/toji-comms-model <model>
/toji-comms-mode discuss|ask|critique|decide|verify|plan
/toji-comms-new [title]
/toji-plan <message>

| command | purpose | |---|---| | /toji-comms <message> | send a raw message to the peer model | | /toji-comms-model <model> | choose the target peer model | | /toji-comms-mode <mode> | set discussion mode | | /toji-comms-new [title] | start a new comms thread | | /toji-plan <message> | compatibility plan command |

Reproduce the operational benchmark

The benchmark measures Toji core directly, without LLM/session overhead:

• cold index
• hot re-index
• query p50
• project overview p50
• blast-radius p50
• indexed files/symbols/edges

1. Benchmark Toji itself

cd packages/toji-mem
bun run bench --repo . --json

2. Benchmark Flask

From the repository root:

mkdir -p benchmarks/repos
git clone --depth 1 https://github.com/pallets/flask.git benchmarks/repos/flask
cd packages/toji-mem
bun run bench --repo ../../benchmarks/repos/flask --json

If Flask is already cloned:

git -C benchmarks/repos/flask pull --ff-only
cd packages/toji-mem
bun run bench --repo ../../benchmarks/repos/flask --json

Current smoke scores

| repo | cold index | hot index | query p50 | overview p50 | blast p50 | files | symbols | edges | |---|---:|---:|---:|---:|---:|---:|---:|---:| | packages/toji-mem | 679.02 ms | 5.18 ms | 0.68 ms | 0.75 ms | 1.71 ms | 20 | 98 | 647 | | flask | 1888.94 ms | 12.85 ms | 0.71 ms | 9.67 ms | 0.29 ms | 83 | 1620 | 7658 |

RepoBench retrieval scores

Toji also has a local RepoBench Python v1.1 adapter for cross-file retrieval quality. It materializes synthetic repos grouped by repo_name, indexes them, then queries with the gold identifier plus repo/current-file context.

| split | rows | files | Path Hit@1 | Path Hit@5 | Path MRR | Symbol Hit@1 | Symbol Hit@5 | Symbol MRR | p95 latency | |---|---:|---:|---:|---:|---:|---:|---:|---:|---:| | cross_file_first | 8,026 | 17,081 | 0.576 | 0.600 | 0.587 | 0.540 | 0.551 | 0.545 | 0.784 ms | | cross_file_random | 7,610 | 16,750 | 0.513 | 0.544 | 0.526 | 0.467 | 0.478 | 0.471 | 1.014 ms |

Compared to the original name-only baseline, repo/import-aware reranking improves Path Hit@1 by about 13 points on both splits.

Benchmark notes

• CLI benchmark is the source of truth for stable operational numbers.
• /toji-bench uses the same benchmark engine from inside Pi.
• Cloned benchmark repos are scratch data and are not committed.
• Full RepoBench tables live in packages/toji-mem/README.md.