diff --git a/manifests.json b/manifests.json index d1110a1..ce5535a 100644 --- a/manifests.json +++ b/manifests.json @@ -84,7 +84,7 @@ { "id": "deep-research", "name": "deep_research", - "description": "Protocol-first, gated, multi-agent literature investigation. Two human-in-the-loop gates bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer); every claim a synthesis ships must be backed by a row in research_evidence with a verbatim quote_span — if a claim can't produce its quote, the claim gets cut. v0.1.0 ships the protocol (SKILL.md), DB schema (PostgreSQL + SQLite), five agent role prompts, install-manifest, and a worked example (cholesterol primary prevention). Agent-runtime-agnostic — the reference implementation uses the Claude Agent SDK, but the workflow only requires subagent fan-out, persistent KV, scholarly HTTP, and a human-in-loop checkpoint surface. Python reference impl (scholar adapter + synthesis_doc_builder) lands in v0.2.0.", + "description": "Protocol-first, gated, multi-agent literature investigation. Two human-in-the-loop gates bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer); every claim a synthesis ships must be backed by a row in research_evidence with a verbatim quote_span — if a claim can't produce its quote, the claim gets cut. v0.1.0 shipped the protocol (SKILL.md), DB schema (PostgreSQL + SQLite), five agent role prompts, install-manifest, and a worked example (cholesterol primary prevention). v0.2.0 adds the Python reference implementation: a stdlib-urllib scholar adapter (OpenAlex / Semantic Scholar / PubMed / arXiv / Europe PMC / Crossref / Unpaywall) and a python-docx + matplotlib synthesis builder with pluggable upload. Agent-runtime-agnostic; core stays stdlib-only, the docx builder is gated behind the optional [viz] extra.", "capabilities": [ "research", "literature-review", diff --git a/registry/deep-research/index.html b/registry/deep-research/index.html index 112dbe4..cf65028 100644 --- a/registry/deep-research/index.html +++ b/registry/deep-research/index.html @@ -623,7 +623,7 @@
runtime: python-module · install method: git · entrypoint: python -m deep_research
deep_research is an agent-runtime-agnostic workflow that turns an empirical research question into a citation-grade synthesis. Two human-in-the-loop gates (protocol pre-registration, Pass-2 spend) bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer). Every claim a synthesis ships must be backed by a row in the research_evidence table with a verbatim quote_span; claims without their quote get cut. The v0.1.0 distribution ships the protocol (SKILL.md), DB schema (PostgreSQL + SQLite), five agent role prompts, and a worked example. The Python reference implementation (scholar adapter + synthesis_doc_builder) lands in v0.2.0.
+deep_research is an agent-runtime-agnostic workflow that turns an empirical research question into a citation-grade synthesis. Two human-in-the-loop gates (protocol pre-registration, Pass-2 spend) bracket a four-role subagent crew (Scout / Skeptic / Methodologist / Synthesizer). Every claim a synthesis ships must be backed by a row in the research_evidence table with a verbatim quote_span; claims without their quote get cut. v0.2.0 adds the Python reference implementation: a stdlib-urllib scholar adapter (OpenAlex / Semantic Scholar / PubMed / arXiv / Europe PMC / Crossref / Unpaywall) and a python-docx + matplotlib synthesis builder with pluggable upload. Core stays stdlib-only; the docx builder is gated behind the optional `[viz]` extra.
Tags: researchliterature-reviewmeta-analysisagentssubagent-fan-outno-fabricationskill-bundle
License: Apache-2.0
Last fetched 2026-06-01T20:33:24Z (live)