Keyless evidence gathering
The core gather_bundle workflow searches and extracts public sources without making an API key the entry ticket.
OPEN-SOURCE · MCP · WEB RESEARCH
Sibyl.
Research the web as inspectable evidence—or produce a cited report with your model.
Sibyl is a web-research MCP, CLI, and Python library. Its keyless path returns a typed SourceBundle with passage provenance and explicit insufficiency states; its optional model-backed path synthesizes the evidence into a cited report.
HOW IT WORKS
A bounded path from request to evidence.
- 01
Search
Gather public-web candidates without requiring a search API key for the core retrieval path.
- 02
Extract
Turn pages into compact, ranked passages that retain URLs, offsets, identifiers, and content hashes.
- 03
Distinguish
Cluster syndicated copies so repeated text is not mistaken for multiple independent sources.
- 04
Hand off
Return a typed SourceBundle with diagnostics and an explicit sufficient, partial, or insufficient state.
DESIGN
The product is the contract.
The interface is useful because it exposes what happened, where confidence comes from, and where the system stops—not because an agent produced a confident paragraph.
Passage-level provenance
Citation IDs, character offsets, source URLs, and hashes let downstream agents inspect the exact evidence they received.
Independent-support signals
content_cluster_id groups syndicated or substantially duplicated material instead of counting domains alone.
Honest failure states
Typed status and diagnostics make missing, partial, or low-quality support visible instead of quietly filling the gap.
MCP, CLI, and Python
Use the same retrieval layer from an MCP host, a terminal workflow, or directly inside a Python application.
Optional report synthesis
A configured language model can turn the evidence bundle into a cited report; retrieval remains useful without one.
QUICK START
Inspect the real thing.
Then ask your MCP host to gather evidence for a question. The keyless path returns structured sources even when no synthesis model is configured.
TERMINALPUBLIC BETA · v0.3.0
$ python -m pip install sibyl-research
$ claude mcp add sibyl -- uvx --from sibyl-research sibyl-mcpVERIFIABLE SCOPE
- 221
- automated tests
- BETA
- current maturity
- 8 / 8
- fixed retrieval evaluation
- 3.10–3.12
- tested Python versions
The 8/8 result is a deterministic lexical retrieval evaluation, not a claim that the live web is complete or always correct. The source-quality baseline separately reports 83.3% selective accuracy at 75% coverage.
HONEST BOUNDARIES
What this does not prove.
- 01Retrieval is evidence collection, not a truth oracle; important claims still require judgment and source review.
- 02Search snippets are discovery leads, not equivalent to evidence extracted from the underlying page.
- 03Different domains can repeat the same wire copy, which is why Sibyl exposes content clusters rather than treating domain count as independence.
- 04One-shot report quality depends on the configured model, while the evidence bundle remains inspectable without synthesis.
- 05The keyless path depends on public search and publisher availability, so repeated results can vary or be throttled; the project remains a public beta until its dated live launch gate passes.
- 06Optional third-party extraction services receive the URLs they are asked to process; use the local path when that disclosure is inappropriate.
FAQ
Before you try it.
Does Sibyl require a search API key?
No for its core public-web retrieval path. Optional providers and model-backed report synthesis may have their own credentials, but structured evidence gathering is designed to work keylessly.
Does Sibyl always write a finished research report?
No. Its primary product is a typed evidence bundle. A configured model can synthesize that bundle into a cited report, but downstream agents can also inspect or compose from the evidence directly.
Do three different domains count as three independent sources?
Not necessarily. Sibyl clusters substantially duplicated or syndicated content so repeated copies can be recognized as one underlying line of support.
Does a sufficient status mean the claim is true?
No. Sufficiency describes whether the retrieval contract found enough usable evidence for the requested task. It does not replace source criticism or factual judgment.
OPEN SOURCE