Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Daedalus Context Graph

Pre-alpha skeleton for Daedalus Context Graph, a reusable context graph kernel for AI agents and context engineering.

Daedalus Context Graph is a small, reusable kernel for building context graphs: scoped context cores, typed nodes and edges, provenance, decision traces, retrieval policies, and adapter boundaries. It is designed to stay useful outside Hermes while providing a clean path for a Hermes Agent memory-provider adapter.

Maintained by Dr. Mani Saint-Victor / BionicButterfly13: BionicButterfly.me.

Status

This package is pre-alpha. The code is MIT licensed, but the repository remains publicly visible once the initial skeleton is pushed.

This initial alpha exists to reserve the public package name and make the kernel installable while the API remains explicitly pre-alpha.

Install

Install the current skeleton from PyPI after the first alpha upload:

python -m pip install daedalus-context-graph

For GitHub-based development:

git clone https://github.com/bionicbutterfly13/daedalus-context-graph.git
cd daedalus-context-graph
python -m pip install -e ".[dev]"
pytest -q

Context Engineering Focus

The package is aimed at the current context-engineering wave: portable context cores, provenance-aware graph memory, decision traces, retrieval policies, and adapter surfaces for agent runtimes.

Package Strategy

The public package is the kernel. Hermes integration stays thin and optional:

  • General Python users install daedalus-context-graph for the context graph kernel.
  • Hermes users install a Hermes plugin/provider that depends on the kernel.

Current Skeleton

Implemented now:

  • DecisionTrace
  • ContextGraphStore protocol
  • EntityRef
  • ArtifactRef
  • EvidenceStandard
  • WorkflowVersion
  • InMemoryDaedalusGraph
  • Basic precedent search filters
  • JSON export surface

Planned:

  • Context core schema and namespace model.
  • Neo4j-backed store.
  • Ontology and active metadata layer.
  • Governed retrieval and access policy.
  • MCP server.
  • Hermes adapter/provider.
  • PyPI release workflow.

API reference: docs/API.md.

Contribution guide: CONTRIBUTING.md.

Local Checks

cd daedalus-context-graph
PYTHONPATH=src pytest -q
python -m compileall src
python -m build --sdist --wheel
python -m twine check dist/*

Metadata

Release files for daedalus-context-graph 0.1.0a0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for daedalus-context-graph 0.1.0a0
File Size Uploaded
daedalus_context_graph-0.1.0a0.tar.gz 13.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for daedalus-context-graph 0.1.0a0
File Interpreter ABI Platform
daedalus_context_graph-0.1.0a0-py3-none-any.whl Python 3 none any Details

Total release size: 21.5 kB

Release files / daedalus_context_graph-0.1.0a0.tar.gz

Download URL daedalus_context_graph-0.1.0a0.tar.gz
Size 13.8 kB
Tags Source
SHA-256 checksum
How to use checksums
775d0422b6ff3e07e1c949c2499bbfc094032f9d900a8c73e9bfdcd74fa12d97
BLAKE2b-256 checksum
How to use checksums
8ba1770f87493311543d5d7b86c81095e0c42135004cbd4d07e637133ac18803
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

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 May 24, 2026.

Transparency log

Release files / daedalus_context_graph-0.1.0a0-py3-none-any.whl

Download URL daedalus_context_graph-0.1.0a0-py3-none-any.whl
Size 7.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9564e171dea9986ed1f24753696f0379aae32954b88e9c38a50cc2d4fe725f3d
BLAKE2b-256 checksum
How to use checksums
ec66f038b41fde0ef2cf0eb157fab2ddae05f7264653a88cba07edd5c53cbac6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

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 May 24, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0a0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page