Eidos: Git-Native AI Software Development Ecosystem
Eidos is an open, Git-native, agent-agnostic development framework designed to unify product definition, architectural invariants, and autonomous coding agents under executable living specifications.
This repository dogfoods the Eidos Specification Standard to define Eidos itself.
Quickstart
# Install with uv (recommended)
uv add --dev eidos-ai
# Or with pip
pip install eidos-ai
# Initialize Eidos in your repository
eidos init
# Validate living specifications
eidos validate eidos
# Verify zero drift between code and living specs
eidos drift
# Launch interactive C4 architecture portal
eidos serve --path eidos --port 8080
# Install AI agent plugin (14 skills for Antigravity, Claude, Cursor, Copilot)
eidos plugin install --target all
Repository Architecture
eidos/
├── pyproject.toml # Modern Python package definition (eidos-ai on PyPI)
├── zensical.toml # Zensical documentation site configuration
│
├── src/eidos/ # [THE ENGINE / SOLUTION]
│ ├── cli/ # CLI commands (`eidos validate`, `eidos drift`, `eidos delta`, etc.)
│ ├── core/ # AsciiDoc + YAML frontmatter parser & schema validator
│ ├── plugin/ # Agent plugin packager, validator, and installer (14 skills)
│ ├── portal/ # Interactive Living Architecture static portal generator
│ ├── vcs/ # Git spec-to-code drift detection & reconciliation engine
│ └── schemas/v1/ # Portable JSON/YAML Schemas bundled as package data
│
├── eidos/ # [THE LIVING SPECIFICATION / REAL USAGE]
│ ├── system.adoc # Root system descriptor
│ ├── personas/ # Human & AI actor roles
│ ├── policies/ # Non-negotiable architectural invariants (POL-*)
│ ├── domains/ # Bounded contexts & capabilities (CAP-*)
│ ├── architecture/ # System architecture, components, & contracts
│ └── deltas/ # In-flight and applied mutations (DLT-*)
│
├── docs/ # User documentation site (Zensical)
└── tests/ # Engine & specification test suites
Key Distinctions from Existing Tools
| Dimension | Traditional / Existing Tools | Eidos Approach |
|---|---|---|
| Scope | Coding loop only (Aider, Claude Code) or monolithic bot (Devin) | Full SDLC: Exploration → Product Baseline → SpecDelta → Code → CI |
| Specifications | Ephemeral Jira tickets, stale Confluence/Notion pages | Versioned YAML frontmatter + AsciiDoc living in Git |
| Change Management | Narrative RFC essays that rot in archive folders | Declarative SpecDelta mutations applied automatically upon merge |
| Agent Support | Vendor-locked to a single proprietary LLM | Agent-agnostic via agent-plugins.org v1.0.0 & CLI-first Agent Skills |
| VCS Support | GitHub-only or closed web UI | Native bidirectional support for both GitHub and GitLab |
Navigating the Specifications
- Root System:
eidos/system.adoc - Product Domains:
- Policies:
- Technical Architecture:
- SpecDeltas:
Documentation & Living Portal
- User Documentation: https://mchawa.github.io/eidos/
- Interactive Living Architecture Portal: https://mchawa.github.io/eidos/portal/
- PyPI Package: https://pypi.org/project/eidos-ai/
- AI Agent Plugin Guide: https://mchawa.github.io/eidos/guides/agent-plugin/
License
Licensed under the MIT License.
Metadata
Release files for eidos-ai 0.5.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| eidos_ai-0.5.0.tar.gz | 606.9 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| eidos_ai-0.5.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.0 MB
Release files / eidos_ai-0.5.0.tar.gz
| Download URL | eidos_ai-0.5.0.tar.gz |
|---|---|
| Size | 606.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bc8ba8f09601eb7c0712396c77cfdc26220ff3376685c0ac293d95efe00e2b95
|
|
BLAKE2b-256 checksum How to use checksums |
9750777d0669dd4f0710b2bcbf0dd6187d9d6db0eee05bbd05847c75547dc225
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 12, 2026.
Transparency logRelease files / eidos_ai-0.5.0-py3-none-any.whl
| Download URL | eidos_ai-0.5.0-py3-none-any.whl |
|---|---|
| Size | 396.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
63638c132ade406352c2250fface9284121f680854aed9d363a336486d83521b
|
|
BLAKE2b-256 checksum How to use checksums |
f0618907550709c3bb7a94df126e345fc594b31fa68a4af0ad3c6dad258342b5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 12, 2026.
Transparency logSecurity for eidos-ai 0.5.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for eidos_ai-0.5.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 12, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.