App
Langfuse
Langfuse is an open-source LLM engineering platform (GitHub) that helps teams collaboratively debug, analyze, and iterate on their LLM applications.
What your agent can do with Langfuse
Triggers and actions 1 trigger · 13 actions
- TriggerNew Trace
Polling trigger: fires for newly created traces (dedup by trace id / timestamp). GET /api/public/traces
- ActionAdd Comment
Add a comment to a trace/observation/session/prompt object. POST /api/public/comments
- ActionAdd Dataset
Create a new dataset. POST /api/public/v2/datasets
- ActionAdd Dataset Item
Create an item (input/expected_output/metadata) in a dataset. POST /api/public/dataset-items
- ActionAdd Prompt
Create a new prompt version (text or chat). POST /api/public/v2/prompts
- ActionAdd Score
Create a score attached to a trace/observation/session (numeric, categorical, or boolean). POST /api/public/scores
- ActionDelete Trace
Delete a trace by id. DELETE /api/public/traces/{traceId}
- ActionGet Project
Reads the Langfuse project that the connection's project-scoped API key belongs to.
- ActionGet Prompt
Get a prompt by name (and optional version/label). GET /api/public/v2/prompts/{promptName}
- ActionGet Trace
Get a single trace by id, including nested observations/scores. GET /api/public/traces/{traceId}
- ActionList Dataset Items
List items in a dataset. GET /api/public/dataset-items
- ActionList Datasets
List all datasets in the project. GET /api/public/v2/datasets
- ActionList Prompts
List all prompts in the project. GET /api/public/v2/prompts
- ActionList Scores
List scores with optional filters. GET /api/public/v2/scores
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Not listed?
Need a trigger or action that is not here?
Ask your agent. Describe what you need in plain language and it reads the Langfuse API documentation, builds the operation at whatever depth the API allows, tests every branch and ships it. The list above is what exists today, not the limit.