D
docxology/codomyrmex
Modular Python coding and agent platform — LLM agents, graph RAG, static analysis, git ops, cloud and…
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
- Star count
- 10 ★ · docxology/codomyrmex · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-05 · last seen 2026-11-14 · seen 10× · listed by 2 sources
- Score
- score 203 · 10 ★ · 2 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
docxology/codomyrmex;first catalogued 2026-11-05;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# 🐜 Codomyrmex
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
> A comprehensive, modular, agentic Python ecosystem for software engineering, personal AI infrastructure, and multi-agent orchestration.
Codomyrmex is a modular library of 132 top-level modules under src/codomyrmex/ spanning AI agents, cloud infrastructure, security, finance, multimedia, and more. The count is honest (every directory has an init.py) — roughly 25 modules are substantial production surfaces (agents, llm, cloud, security, coding, documentation, orchestrator, etc.), ~75 are legitimate but narrower utilities, and ~30 are teaching/exploratory modules (dpo, nas, ssm, softmaxopt, etc.) that demonstrate techniques rather than ship production workflows. A documented Zero-Mock policy governs the active test suites, while the measured quality gates and inventory describe what was actually checked in a given run; they do not imply that every method is complete or production-safe. In the complete locked dependency profile, the ecosystem exposes 622 runtime MCP tools in the generated manifest and 632 production @mcptool decorator lines in Python sources for Claude, Gemini, GPT, and any Model Context Protocol client (docs/reference/inventory.md). It includes 3,000+ Python files, 37,060 collected tests (uv run --locked --all-extras --group docs python scripts/docinventory.py --pytest), 1,217 Markdown files under docs/, and 37 GitHub Actions workflows (.github/workflows/.yml). These are measured snapshot values for that dependency profile; refresh the linked inventory before treating them as current.
## Technical report
The source-bound Codomyrmex v1.3.0 technical report is archived as a Zenodo record family: concept DOI 10.5281/zenodo.21750800, version DOI 10.5281/zenodo.21750801, and GitHub release v1.3.0-paper. The report documents implementation contracts and controlled fixtures; it does not claim external effectiveness, calibration, or production safety.
bash
# Install
git clone https://github.com/docxology/codomyrmex.git && cd codomyrmex
uv sync --locked --all-groups
# Verify
uv run codomyrmex doctor --all
## 📋 Table of Contents
Documentation Hub
System Architecture
Module Inventory
Module Dependency Architecture
Agent Orchestration Pipeline
Project Structure
Aggregate Statistics
LLM Provider Matrix
Agent Dispatch Architecture
Testing Philosophy
Configuration Architecture
Personal AI Dashboard
Quick Start
Documentation Standards
GitHub Actions Workflows
License
## ✨ Why Codomyrmex?
| 🧩 132 Top-Level Modules | Packages under src/codomyrmex/ — modular interfaces with scoped zero-mock tests |
| 🤖 622 Runtime MCP Tools | Complete locked dependency profile; 632 source @mcptool decorator lines; see inventory |
| 🧪 37,060 Collected Tests | Complete locked dependency profile; uv run --locked --all-extras --group docs python scripts/docinventory.py --pytest; zero-mock policy |
| 🔒 Security First | GitGuardian, SBOM, GGSHIELD pre-commit, detect-secrets integration |
| 🎛️ 13+ Agent Providers | Claude, Gemini, GPT-4o, DeepSeek, Mistral, Jules, Codex, Pi, and more |
| 🔬 ML Research Ready | LoRA, RLHF, DPO, distillation, quantization, NAS, Mamba SSM, autograd |
| 🏠 Personal AI Infrastructure | Email, calendar, finance, wallet, dashboard — full PAI toolbox |
Codomyrmex is a modular library of 132 top-level modules under src/codomyrmex/ spanning AI agents, cloud infrastructure, security, finance, multimedia, and more. The count is honest (every directory has an init.py) — roughly 25 modules are substantial production surfaces (agents, llm, cloud, security, coding, documentation, orchestrator, etc.), ~75 are legitimate but narrower utilities, and ~30 are teaching/exploratory modules (dpo, nas, ssm, softmaxopt, etc.) that demonstrate techniques rather than ship production workflows. A documented Zero-Mock policy governs the active test suites, while the measured quality gates and inventory describe what was actually checked in a given run; they do not imply that every method is complete or production-safe. In the complete locked dependency profile, the ecosystem exposes 622 runtime MCP tools in the generated manifest and 632 production @mcptool decorator lines in Python sources for Claude, Gemini, GPT, and any Model Context Protocol client (docs/reference/inventory.md). It includes 3,000+ Python files, 37,060 collected tests (uv run --locked --all-extras --group docs python scripts/docinventory.py --pytest), 1,217 Markdown files under docs/, and 37 GitHub Actions workflows (.github/workflows/.yml). These are measured snapshot values for that dependency profile; refresh the linked inventory before treating them as current.
## Technical report
The source-bound Codomyrmex v1.3.0 technical report is archived as a Zenodo record family: concept DOI 10.5281/zenodo.21750800, version DOI 10.5281/zenodo.21750801, and GitHub release v1.3.0-paper. The report documents implementation contracts and controlled fixtures; it does not claim external effectiveness, calibration, or production safety.
bash
# Install
git clone https://github.com/docxology/codomyrmex.git && cd codomyrmex
uv sync --locked --all-groups
# Verify
uv run codomyrmex doctor --all
## 📋 Table of Contents
Documentation Hub
System Architecture
Module Inventory
Module Dependency Architecture
Agent Orchestration Pipeline
Project Structure
Aggregate Statistics
LLM Provider Matrix
Agent Dispatch Architecture
Testing Philosophy
Configuration Architecture
Personal AI Dashboard
Quick Start
Documentation Standards
GitHub Actions Workflows
License
## ✨ Why Codomyrmex?
| 🧩 132 Top-Level Modules | Packages under src/codomyrmex/ — modular interfaces with scoped zero-mock tests |
| 🤖 622 Runtime MCP Tools | Complete locked dependency profile; 632 source @mcptool decorator lines; see inventory |
| 🧪 37,060 Collected Tests | Complete locked dependency profile; uv run --locked --all-extras --group docs python scripts/docinventory.py --pytest; zero-mock policy |
| 🔒 Security First | GitGuardian, SBOM, GGSHIELD pre-commit, detect-secrets integration |
| 🎛️ 13+ Agent Providers | Claude, Gemini, GPT-4o, DeepSeek, Mistral, Jules, Codex, Pi, and more |
| 🔬 ML Research Ready | LoRA, RLHF, DPO, distillation, quantization, NAS, Mamba SSM, autograd |
| 🏠 Personal AI Infrastructure | Email, calendar, finance, wallet, dashboard — full PAI toolbox |
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/docxology-codomyrmex/)
- Source
- github · https://github.com/docxology/codomyrmex
- Browse by field
- Open source
- Traction
- 10 ★
- Listed by
- 2 independent sources
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.