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.