ceven

Bitquery

Streams indexed blockchain data into your workflows, monitors on chain movements in real time, and calculates complex network metrics across forty different chains.

Try Bitquery in Ceven

Ask Ceven anything
Standard

Why use Ceven?

  1. AI native Bitquery integration

    • Describe the outcome and Ceven picks the right Bitquery calls, fills the parameters, and checks the result.
    • Structured, agent friendly tool schemas so each call runs reliably instead of by guesswork.
    • Rich coverage for reading, writing, and querying your Bitquery data, across all 10 of its actions.

  2. Managed auth

    • Built in OAuth with automatic token refresh and rotation.
    • One place to manage, scope, and revoke Bitquery access.
    • Per user and per environment credentials instead of shared keys.

  3. Agent optimized design

    • Actions are tuned from real success and error rates so reliability climbs over time.
    • Full execution logs so you always know what ran in Bitquery, when, and on whose behalf.
    • The agent pauses and asks when Bitquery is unclear instead of plowing ahead.

  4. Enterprise grade security

    • Fine grained access so you control which agents and people can reach Bitquery.
    • Least privilege by default, read scopes first and only the writes a workflow needs.
    • A full audit trail of every Bitquery action to support review and sign off.

Supported tools

Every action Ceven's agents can run on Bitquery, and when to use it.

Archive Database Query
Use this when you need full historical blockchain data that is delayed by minutes or hours.
Combined Database Query
Use this when you need both historical and up to the second blockchain data in one request.
Realtime Database Query
Pull the most recent indexed blockchain data for immediate analysis.
Mempool Subscription
Use this after constructing a GraphQL subscription to stream pending transactions live for EVM chains.
Network Selection
Use this before constructing dataset queries to ensure the correct blockchain network is targeted.
Database Selection
Use this to select archive, realtime, or combined databases at the top level of a request.
Sum Metric
Calculate the total sum of a specified field across defined dimensions for aggregation.
Count Distinct Metric
Use this to aggregate the number of unique occurrences for a specific field in a dataset.
Quantile Metric
Calculate percentiles such as the median or quartiles to understand numerical data distribution.
Statistics Metric
Compute precise summary statistics like mean or median over one variable in a dataset.
Price Asymmetry Metric
Use this to filter trades based on the price asymmetry metric for trading signals.
Options Query
Fetch GraphQL dataset options via schema introspection to discover root level query fields.
Conditional Metrics Snippet
Generate a metric snippet with conditional logic to apply filters directly on calculations.
Count Metric
Use this for simple record counts of items matching a GraphQL query.
Uniq Metric
Estimate the count of unique values for high level analytics on large blockchain datasets.
Aliases Metric
Use GraphQL aliases to rename fields in the response when querying multiple identical metrics.
Early Access Program Query
Tool to access streaming data across various blockchain networks for evaluation purposes. use when querying chains not available via the v2 endpoint; limited to real time data only.
Select By Metric
Tool to generate a graphql metric snippet filtering by its value using selectwhere. use when you need to include only metrics meeting specific value conditions (e.g., only positive sums).

18 actions · scroll to see them all

Frequently asked questions

Ceven intelligently switches between the archive, realtime, and combined databases based on your request. If you ask for a trend over the last three years, the agent selects the archive database to minimize cost and maximize historical depth. If you ask what is happening right now, it targets the realtime database. For complex requests that bridge the gap, it uses the combined database. The agent manages the database selection tool automatically so you do not have to specify the layer in your natural language prompt, though you can override this if you have a specific preference for data latency or precision.
Yes, Ceven leverages the Bitquery mempool subscription to track pending transactions. When you set up a workflow to watch for specific conditions, the agent establishes a websocket connection via Bitquery. It filters the incoming stream for the criteria you defined, such as transaction value or target contract address. Once a match is found, the agent can trigger downstream actions like sending a notification or executing a trade. This allows you to react to on chain events before they are even confirmed in a block, providing a significant advantage for latency sensitive operations.
The Early Access Program allows Ceven to query chains that are not yet available via the standard v2 endpoint. However, this comes with a major quirk: it only provides real time data. You cannot use the Early Access Program for historical backtesting or archive queries. If your workflow requires a mix of historical context and live data for a new chain, the agent will notify you that historical data is unavailable and will only provide the most recent events. Once the chain moves to the general v2 endpoint, the agent automatically restores full archive access.
You do not need to know GraphQL to use Bitquery through Ceven. The agent acts as a translator that converts your natural language requests into precise GraphQL queries. It uses the options query tool to perform schema introspection, meaning it checks the current API capabilities before writing the query. If a request requires complex aggregations, the agent utilizes the specific metric tools like sum, count distinct, or quantiles to build a valid snippet. If the API returns an error, the agent analyzes the response and self corrects the query syntax in real time.
Ceven can access any of the forty plus chains supported by Bitquery. The only limitation is the rate limit associated with your specific Bitquery API tier. Different tiers have different points per second allocations. If a workflow triggers a high volume of requests that exceeds your tier limit, Bitquery will return a rate limit error. Ceven handles this by implementing an exponential backoff strategy, queuing the requests and retrying them automatically to ensure no data is lost, although this may introduce a slight delay in the delivery of your results.
Yes, this is a core strength of the integration. You can ask Ceven to find wallets that exhibit specific behaviors, such as those that bought a token within ten minutes of a specific event. The agent will use the combined database to search for the event, identify the interacting addresses, and then run a separate query to analyze the historical behavior of those wallets. It can then aggregate these addresses into a list or sync them to a CRM or database for further tracking, effectively automating the process of on chain forensics.
Bitquery provides two ways to count unique values. The count distinct metric provides an exact count, which is highly accurate but more computationally expensive and slower for massive datasets. The uniq metric provides an estimated count using probabilistic algorithms, which is significantly faster for extremely large datasets where a small margin of error is acceptable. Ceven chooses the tool based on the scale of the data and your need for precision. If you explicitly ask for an exact number, the agent will prioritize the count distinct tool.
Ceven does not store the raw blockchain data permanently. It treats Bitquery as a real time data source. When a workflow runs, the agent pulls the necessary data into a short lived context window to perform calculations or generate reports. Once the workflow completes and the final action is taken, the raw data is cleared. If you need to keep a permanent record of the data, you can instruct the agent to push the results into your own data warehouse, a Google Sheet, or a database as part of the workflow design.

Alternatives to Bitquery

Other tools that solve a similar problem. Ceven supports these too, so you can switch or run more than one at once.

The Graph logoThe GraphDune Analytics logoDune AnalyticsNansen logoNansen

Try Ceven on your stack

Plug Ceven on top of the tools you already run. Connect Bitquery and the rest of your stack, describe the outcome, and its agents handle the work end to end, days of it in minutes.

Get started for free