AgentGraph Feed Connector

The AgentGraph Feed Connector shares local observations, bookmark changes, and explicit deletions through a separately deployed AgentGraph feed server.

Installation

Install the connector into the same Python environment as AgentGraph:

uv pip install agentgraph-connector-feed

The 0.1.x connector releases support agentgraph-server>=0.6.1,<0.7.

Configuration

Configure the feed server base URL, then inspect the saved configuration:

agentgraph connector feed configure http://localhost:8767
agentgraph connector feed status

The configured URL must not include /events or /events-feed. The connector adds /events and /events/tail when it publishes and polls respectively. For a deployed server behind a reverse proxy, configure the URL at which those endpoints are exposed.

The connector publishes new local observations, bookmark changes, and explicit deletions as best-effort HTTP requests. It polls the feed once per minute. Its first poll starts at the current feed tail, so existing events are not imported.

The server must expose POST /events, GET /events, and GET /events/tail. The connector and server communicate only through this HTTP API; the server is deployed and maintained separately.

Security

The feed is unauthenticated and should only be exposed on a trusted network.

Development

uv sync --locked
uv run pytest
uv run pyright
uv run ruff check .
uv run ruff format --check .

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentgraph_connector_feed-0.1.1.tar.gz (7.4 kB view details)

Uploaded Aug 30, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

agentgraph_connector_feed-0.1.1-py3-none-any.whl (6.5 kB view details)

Uploaded Aug 30, 2026 Python 3

File details

Details for the file agentgraph_connector_feed-0.1.1.tar.gz.

File metadata

Download URL: agentgraph_connector_feed-0.1.1.tar.gz
Upload date: Aug 30, 2026
Size: 7.4 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for agentgraph_connector_feed-0.1.1.tar.gz
Algorithm	Hash digest
SHA256	`f6931c2cad6a80d2a18980dac52ce1e2730a779342532cd6b9c249671e34e25c`
MD5	`f8dd3fc34123964f55b7bf0ef522f5d5`
BLAKE2b-256	`449776038c6ee1cdf8bfd93d219420c4258af6c888322c9b79fe2bfd39ec8805`

See more details on using hashes here.

Provenance

The following attestation bundles were made for agentgraph_connector_feed-0.1.1.tar.gz:

Publisher: pypi-release.yml on simonexmachina/agentgraph-connector-feed

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: agentgraph_connector_feed-0.1.1.tar.gz
- Subject digest: f6931c2cad6a80d2a18980dac52ce1e2730a779342532cd6b9c249671e34e25c
- Sigstore transparency entry: 2655856976
- Sigstore integration time: Aug 30, 2026
Source repository:
- Permalink: simonexmachina/agentgraph-connector-feed@f08221e9a4353d2a7d0ede176039a5a3f2bfb933
- Branch / Tag: refs/tags/v0.1.1
- Owner: https://github.com/simonexmachina
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: pypi-release.yml@f08221e9a4353d2a7d0ede176039a5a3f2bfb933
- Trigger Event: push