Canny + Cognee: a feedback connector for AI agent memory

Description and use

After syncing, Canny posts with votes and comments are ingested into Cognee’s knowledge graph, enabling queries about top feature requests and why users want them.

Problem

Product teams need to answer what users want most and why, but Canny’s comments are scattered across posts.

Outcome

After syncing, Cognee can answer complex questions about feature requests, combining vote counts and comment analysis in a single query.

Workflow

• Install cognee-community-connector-canny (pins cognee==1.4.0).
• Export CANNY_API_KEY and LLM_API_KEY (or pass api_key=).
• Call cognee.remember(canny_source(), dataset_name="canny").
• Query with cognee.search(query_text="Which feature requests have the most votes, and why do users want them?", query_type=cognee.SearchType.GRAPH_COMPLETION, datasets=["canny"]).

Evidence

Short answer: install cognee-community-connector-canny, set CANNY_API_KEY and LLM_API_KEY, and pass canny_source() to cognee.remember().

Source

After a sync, cognee.search answers questions against the graph.

Source

Canny’s posts/list endpoint has no "updated after" filter, and Canny has no feed of deleted posts.

Source