Rust deep research engine with multi-agent debate — a Feynman-style deepresearch
pipeline with an SQLite-backed queue, MCP server, and five source types.
Multi-agent debate: 5 agents with distinct beliefs critique the brief's
content AND references, converge over rounds (spread/convergence measured),
then answer targeted follow-up interviews on open questions
SQLite state machine: every phase commits to research.db — crash
recovery, resume (--resume <id>), audit trail (research_phase_log)
Resilient worker: max 1 concurrent run, batch coherence, unlimited retry
with backoff, auth errors (401/403) fail fast
MCP server (--mcp): 8 tools over stdio for OpenCode/Claude/etc.
Language-aware: Hungarian topics produce Hungarian reports and debates
CLI: run research, --list, --status <id>, --resume <id>
Grab the package for your platform from the
latest release:
Platform
Asset
Arch
Linux
research_mcp-<ver>-linux-x86_64.tar.gz
x86-64
macOS
research_mcp-<ver>-macos-arm64.tar.gz
Apple Silicon (M1+)
# Linux / macOS
tar xzf research_mcp-<ver>-<platform>.tar.gz
cd research_mcp-<ver>
cp config.example.toml config.toml # fill in your API keys
./research_mcp "your research topic"
No Rust toolchain needed — the binaries are self-contained (only system libc).
From source
cargo build --release
cp config.example.toml config.toml # fill in your API keys
OpenRouter model ID (vendor/model); falls back to model
model
no
Model ID for the active backend (default deepseek-v4-flash)
out_dir
no
Report output dir (default /home/user/AIDocumentStore/raw/research)
db_path
no
SQLite path (default ./research.db)
llm_timeout_secs
no
LLM request timeout (default 300)
temperature
no
Drafting temperature (default 0.3)
max_sources
no
Hard cap on full-text downloads per run (default 8)
LLM backend & pro-class gate
llm_backend (config.toml) or --llm-backend (CLI) selects the LLM API:
opencode (default: OpenCode Go) or openrouter (OpenRouter, OpenAI-compatible
chat completions at https://openrouter.ai/api/v1). Each backend uses its own
key/model (openrouter_api_key + openrouter_model for OpenRouter); OpenRouter
model IDs are vendor/model (e.g. deepseek/deepseek-v4-flash).
A pro-class gate (mirroring Feynman) refuses premium "pro" models at
startup regardless of backend — e.g. gpt-5.6-pro, o1-pro — so the pipeline
never silently runs on a paid premium tier. Open-weight models that merely
contain "pro" in the name (deepseek-v4-pro and its routing aliases) are
explicitly allowed.
Adaptive coverage (LLM-driven)
The research planner is an LLM that sizes the search based on topic scale
(Feynman-style "Scale decision"). Two extra plan fields are emitted at planning
time and are not in config.toml:
Plan field
Meaning
Narrow explainer
Broad survey
News / current-events
web_per_query
max web results to collect per query
~6
10–15
15–20
download_budget
desired full-text downloads
~6
10–15
up to 20
download_budget is combined with the config max_sources via a double cap:
the actual download count is min(max_sources, download_budget), so you keep a
hard upper bound on cost/context while coverage expands for news-heavy topics.
Plans that omit either field fall back to defaults (6 / 8), keeping old
plans and saved sessions compatible.
Web search resilience: the keyless backend chain is DuckDuckGo → Bing → Brave,
each with bot-gating detection (real challenge markers, checked after parsing
so genuine results are never discarded) and the whole sweep retries before
giving up. When all three are empty/gated, a "0 web results" warning is
surfaced in the run log instead of silently producing an empty brief.
TinyFish backend (optional, recommended): set tinyfish_api_key in
config.toml (free key from https://agent.tinyfish.ai/api-keys — Search never
draws from the wallet) and web search gains a first-tier backend served by a
real browser: live, never-cached results as structured JSON, immune to the
bot-gating that intermittently blocks the keyless scrapers. Without the key
the tier is skipped silently and the keyless chain handles everything.
Usage
CLI
# Run a research (synchronous)
research_mcp "What are the tradeoffs of the ketogenic diet?"
# Query the queue
research_mcp --list
research_mcp --list --list-status complete
research_mcp --status <run_id>
# Resume an interrupted run (crash recovery)
research_mcp --resume <run_id>
# Re-run a job with the same topic and fresh session (test fixes)
research_mcp --rerun <run_id>
# Raise the hard cap on full-text downloads (news/current-events topics)
research_mcp --max-sources 20 "your topic"
# Run as MCP server (stdio)
research_mcp --mcp
MCP (OpenCode)
See docs/opencode.md for the full setup guide (config,
troubleshooting, tool usage). Short version:
Use at your own risk. The software is provided "as is", without warranty
of any kind (see LICENSE.md). Generated research briefs are
AI-assisted and may contain errors, omissions, or hallucinations. Always
verify claims against the cited primary sources. This tool does not provide
professional, medical, financial, or legal advice.
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Perguntas
Como instalo Research?
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Research precisa de uma chave de API?
Este registro não lista nenhuma variável de ambiente obrigatória.
Qual transporte Research usa?
Research roda localmente via stdio.
Quando Research foi verificado pela última vez?
Última verificação: 2026-10-28. Deep research in Rust: 5 source types, multi-agent belief debate, SQLite-backed queue, MCP server for OpenCode