Skip to main content

Open Semantic Agent (OSA)

OpenSSF Best Practices DOI PyPI License

An open spec for publish/subscribe that routes messages by what they mean.

Website: https://opensemanticagent.org · Spec: spec/SPEC.md

OSA sits on top of the message transport you already run (Kafka, NATS, Redis Streams, SQS) and works with whichever model you choose. Each message goes through three checks in order: a free topic match, a cheap similarity check, and an AI judge only when the first two are unsure, under token budgets. Every decision is audited and replayable.

Conventional broker Open Semantic Agent
String topics Semantic subscriptions: subscribe by meaning
Payload delivered as-is Schema mediation: each subscriber gets its own contract
Dedupe by message ID Semantic dedupe: 40 alerts about one incident become 1
Static priority Reasoned urgency, with a recorded rationale
Slow consumer → lag or drop Backlog summarization: a digest instead of a loss
Dead-letter queue Self-healing DLQ: diagnose, repair, retry or escalate
Replay the raw log Briefings: "catch me up on order 123 since Monday"
One reply Consensus fan-in: ask N agents, reconcile the answers
Per-topic ACLs Per-subscriber redaction by clearance
Opaque routing Every decision audited and replayable

Use it from an AI assistant

The spec ships as a small MCP server, so any MCP client (Claude, Cursor, VS Code and others) can read it and check documents against it:

uvx open-semantic-agent          # or: pip install open-semantic-agent

Tools, all read-only: osa_list_sections, osa_get_section, osa_search_spec, osa_get_schema, osa_validate (envelope, subscription manifest, audit record, stream message), osa_list_fixtures, osa_get_fixture. It is listed in the MCP Registry as io.github.opensemanticagent/opensemanticagent.

What's here

Path What it is
spec/SPEC.md The specification (0.2, draft)
schemas/ JSON Schemas for the envelope, subscription manifest, audit record and stream messages. Each $id resolves on the website.
conformance/fixtures/ Routing test vectors that implementations run against
osa/, tests/ The MCP server and its tests. The package bundles the spec, schemas and fixtures.
tools/build_site.py, docs/ The website. pip install markdown && python3 tools/build_site.py rebuilds docs/, which GitHub Pages serves.

Implementations

Building one? Open an issue and we'll list it here.

Contributing

See CONTRIBUTING.md. Spec changes go through a pull request against spec/SPEC.md; changes that affect routing add or update fixtures in conformance/fixtures/. Questions and ideas go to Discussions. Security issues: see SECURITY.md.

If you cite the spec, use CITATION.cff or DOI 10.5281/zenodo.24417032 (all versions).

License

Apache-2.0.

Metadata

Release files for open-semantic-agent 0.2.3

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

Source distribution (sdist)

Source distribution for open-semantic-agent 0.2.3
File Size Uploaded Provenance Actions
open_semantic_agent-0.2.3.tar.gz 40.7 kB With provenance Details for open_semantic_agent-0.2.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for open-semantic-agent 0.2.3
File Interpreter ABI Platform Actions
open_semantic_agent-0.2.3-py3-none-any.whl Python 3 none any Details for open_semantic_agent-0.2.3-py3-none-any.whl

Total release size: 71.5 kB

Release files / open_semantic_agent-0.2.3.tar.gz

Download URL open_semantic_agent-0.2.3.tar.gz
Size 40.7 kB
Tags Source
SHA-256 checksum
How to use checksums
fbb106b99a785dc8fa8a1f4120801b8440b8e94b6a3315d5945e824c35811495
BLAKE2b-256 checksum
How to use checksums
7d2717cc9a46bcd60c98335537e1bd6d60c522d2c14d59289f50295a3d257ce3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 21, 2026.

Transparency log

Release files / open_semantic_agent-0.2.3-py3-none-any.whl

Download URL open_semantic_agent-0.2.3-py3-none-any.whl
Size 30.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d8dc32fa5c19dc40c2209f5003ff5a21ab7add62a86c07d069b9c45ca8c03b16
BLAKE2b-256 checksum
How to use checksums
a0a4b76fe64169c9a5f3544a3e33ed750048f2e1d1303b37417f9479a9251e29
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 21, 2026.

Transparency log

Security for open-semantic-agent 0.2.3

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

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for open_semantic_agent-0.2.3.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 Nov 21, 2026.

Transparency log

A 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.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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