Zero-token knowledge base

TopoExploit | System Maps

Architecture maps, an overview video, and the full documentation set, generated offline from the source code. Nothing here was written by an LLM.

6communities
59files
539imports
2languages
997symbols

Interactive maps

Physics-driven diagrams: drag nodes, click one for its documentation, trace upstream or downstream reach. Maps load their engine from a CDN.

Overview video

Cinematic synthwave overview rendered from real scan data: layers, god nodes, dependency tree, communities, import graph, and code DNA. Open/download readmenator.mp4.

Documentation 38 files

Wiki 11

Concept pages per code community: start with index.md.

Second Brain

readmenator-wiki/index.md

The codebase centres on model.py, init.py, train.py. Architecturally it is 6 layers, dominant utility (45 files) across 7 import-based communities. Recorded...

78 lines~763 tokens
Open raw markdown

eval: inference

readmenator-wiki/community_0_eval_inference.md

Community 0 | 12 files | cohesion 0.58

109 lines~1845 tokens
Open raw markdown

topogpt3: model

readmenator-wiki/community_1_topogpt3_model.md

Community 1 | 12 files | cohesion 0.56

101 lines~1657 tokens
Open raw markdown

topogpt3: inference_hrm

readmenator-wiki/community_2_topogpt3_inference_hrm.md

Community 2 | 8 files | cohesion 0.42

94 lines~1731 tokens
Open raw markdown

topogpt3: tasks

readmenator-wiki/community_3_topogpt3_tasks.md

Community 3 | 7 files | cohesion 0.72

84 lines~1301 tokens
Open raw markdown

topogpt3: jlens

readmenator-wiki/community_4_topogpt3_jlens.md

Community 4 | 5 files | cohesion 0.47

83 lines~1810 tokens
Open raw markdown

eval: data_pipeline

readmenator-wiki/community_5_eval_data_pipeline.md

Community 5 | 4 files | cohesion 0.60

80 lines~1514 tokens
Open raw markdown

orphans

readmenator-wiki/community_6_orphans.md

Community 6 | 11 files | cohesion 0.00

93 lines~1248 tokens
Open raw markdown

Concepts

readmenator-wiki/concepts.md

Second-brain semantic layer: nouns map atomically to file sets (EXTRACTED); verbs aggregate structural edges (INFERRED).

124 lines~2764 tokens
Open raw markdown

Queries

readmenator-wiki/queries.md

Log each answered question here so the wiki compounds. Format: question, answer, cited files.

29 lines~178 tokens
Open raw markdown

Audit Report

readmenator-wiki/REPORT.md

Project: TopoExploit | 2026-10-25 | offline, deterministic

43 lines~361 tokens
Open raw markdown

GraphRAG 1

Community report hierarchy for agents. Query it with: readmenator . ask "question" (or MCP readmenator.graphrag).

GraphRAG Community Reports

readmenator-graphrag/REPORTS.md

Entities: 1163 | Relationships: 3406 | Communities: 7 | Themes: 3 | Text units: 1048

154 lines~4129 tokens
Open raw markdown

Project docs 8

Knowledge base, README, and policies.

Polyglot Codebase Knowledge Graph

KNOWLEDGE_BASE.md

Start here: Statistics Dashboard for scope, God Nodes for blast radius, Architecture Reference for per-file API. Agents: prefer readmenator-agent/INDEX.md +...

4523 lines~139093 tokens
Open raw markdown

TopoExploit

README.md

A 122M parameter complex-valued autoregressive language model trained on

493 lines~5142 tokens
Open raw markdown

eval: inference

readmenator-diagrams/eval_inference.md

eval: inference groups 12 files (py) around loadhumaneval, buildprompt, extractcandidate, runonetest, runonetestsandboxed. Drop-in entry point that...

39 lines~298 tokens
Open raw markdown

overview.md

readmenator-diagrams/overview.md

Static architecture map of 59 files (py, sh) in 6 components: eval: inference, topogpt3: model, topogpt3: inferencehrm, topogpt3: tasks, topogpt3: jlens, eval...

121 lines~1796 tokens
Open raw markdown

topogpt3: inference_hrm

readmenator-diagrams/topogpt3_inference_hrm.md

topogpt3: inferencehrm groups 8 files (py) around countunclosedbrackets, countunclosedfences, isresponsecomplete, extracttailforcontinuation...

29 lines~269 tokens
Open raw markdown

topogpt3: model

readmenator-diagrams/topogpt3_model.md

topogpt3: model groups 12 files (py) around TopoGPT2Config, postinit, setuplogger, setseed, QuaternionOps. Diagnostico estatico de un checkpoint TopoGPT3...

41 lines~316 tokens
Open raw markdown

topogpt3: tasks

readmenator-diagrams/topogpt3_tasks.md

topogpt3: tasks groups 7 files (py) around preprocessingchat, postprocessingchat, fmttooldefs, toolcallstext, applychattemplate. Generic task eval: JSONL cases...

35 lines~289 tokens
Open raw markdown

Security Policy

SECURITY.md

Use this section to tell people about which versions of your project are

21 lines~154 tokens
Open raw markdown

Agent docs 13

Grep-friendly indexes for AI agents (also useful for humans).

API

readmenator-agent/API.md

Depends on: topogpt3/init.py

707 lines~18162 tokens
Open raw markdown

Architecture

readmenator-agent/ARCHITECTURE.md

app.py -> topogpt3/init.py

148 lines~2506 tokens
Open raw markdown

Concepts

readmenator-agent/CONCEPTS.md

Nouns map atomically to file sets (EXTRACTED); verbs aggregate structural edges (INFERRED).

120 lines~4493 tokens
Open raw markdown

Gotchas

readmenator-agent/GOTCHAS.md

These files have the most connections. Changes here have high blast radius.

56 lines~768 tokens
Open raw markdown

Subsystem: eval

readmenator-agent/KB_eval.md

Doc: Aggregate HumanEval result JSONL files into a summary table.

245 lines~2954 tokens
Open raw markdown

Subsystem: misc

readmenator-agent/KB_misc.md

Doc: Serve TopoGPT3 (code) + TopoExploit (red-team) as OpenAI-compatible fallback endpoints for...

8 lines~57 tokens
Open raw markdown

Subsystem: root

readmenator-agent/KB_root.md

Doc: Drop-in entry point that demonstrates how to use the topogpt3 package.

118 lines~1402 tokens
Open raw markdown

Subsystem: tests

readmenator-agent/KB_tests.md

Doc: Checkpoint architecture discovery tests.

198 lines~3798 tokens
Open raw markdown

Subsystem: topogpt3

readmenator-agent/KB_topogpt3.md

Doc: TopoGPT3: complex-valued spectral language model for code.

853 lines~14060 tokens
Open raw markdown

Project Memory

readmenator-agent/MEMORY.md

Generated from 59 files at commit 44dbc9781085. Read this first, then readmenator-wiki/index.md, then readmenator . ask "<question>" for anything specific.

85 lines~1260 tokens
Open raw markdown

Security Findings

readmenator-agent/SECURITY.md

3 lines~10 tokens
Open raw markdown

Symbols

readmenator-agent/SYMBOLS.md

1017 lines~24400 tokens
Open raw markdown

Recipes 5

Step-by-step tasks grounded in this codebase.

Recipe: Add a Function

readmenator-agent/recipes/add-function.md

Find the target file by purpose: grep -in '<topic>' readmenator-agent/INDEX.md

9 lines~99 tokens
Open raw markdown

Recipe: Change a File Safely

readmenator-agent/recipes/change-impact.md

Riskiest file: topogpt3/continuation.py (32 dependents)

9 lines~109 tokens
Open raw markdown

Recipe: Fix a Dependency Cycle

readmenator-agent/recipes/fix-cycle.md

Read cycles: grep -A5 'Dependency Cycles' readmenator-agent/GOTCHAS.md

6 lines~65 tokens
Open raw markdown

Recipe: Fix a Security Finding

readmenator-agent/recipes/fix-security.md

Read findings: grep -n '<file>' readmenator-agent/SECURITY.md

6 lines~69 tokens
Open raw markdown

Recipe: Reduce File Complexity

readmenator-agent/recipes/reduce-complexity.md

Target hotspot: topogpt3/model.py

9 lines~76 tokens
Open raw markdown

How to read these maps

Open any map, then: drag nodes freely while physics settles the rest, search (/) to filter, click a node to focus it with full file documentation, Upstream and Downstream to trace authored reach, Path to probe the exact route between two ids, Lens to compare semantic roles, Play to walk the guided chapters, Stabilize to re-run physics, Theme for dark and light, Export for PNG or typed JSON. Deep links such as #route=a~b restore any reading.