⚡ Powered by Xiaomi MiMo

Five agents.
One cited PDF.

DeepResearch Agent turns any research question into a fully-cited PDF report through a 5-stage long-chain reasoning pipeline. No hallucinated sources. No wasted tabs.

5
Specialized Agents
2
Source Backends
100%
Cited Claims
0
Hallucinated URLs

Why this is different

Generic AI assistants invent citations. DeepResearch Agent re-reads every source before letting a claim into the report.

🧩

Single-responsibility agents

Each agent has one job. Planner plans, Searcher searches, FactChecker verifies. No god-prompts.

🔗

Long-chain reasoning

Multi-step decomposition replaces one giant prompt. Better answers, traceable failures.

Real fact-checking

Every claim re-verified against source text. Unsupported claims dropped before synthesis.

📚

arXiv + web sources

Routes technical questions to arXiv, general questions to the web. Inline numbered citations.

📄

Polished PDF output

ReportLab-rendered with title page, sections, references. Ready to share, not edit.

🔍

Inspectable runs

Every agent input and output saved as JSON. Debug failures, replay successes.

The 5-stage pipeline

Plan → Search → Verify → Synthesize → Write. Each stage's output is the next stage's input — typed and auditable.

Question
🗺️
Planner
decompose
🔎
Searcher
arxiv + web
FactChecker
verify
🧬
Synthesizer
cluster
✍️
Writer
render
📄
PDF

Quickstart

Three commands. One question. One PDF.

# Clone & install git clone https://github.com/teguh407/deepresearch-agent.git cd deepresearch-agent pip install -r requirements.txt # Configure your MiMo API key cp .env.example .env # MIMO_API_KEY=sk-... ← paste from platform.xiaomimimo.com # Run your first research python -m src.main "How does Mixture-of-Experts compare to dense models?" 🧠 DeepResearch Agent v0.1.0 [1/5] 🗺️ Planning sub-questions ............ ✓ 6 sub-questions [2/5] 🔎 Searching sources .................. ✓ 23 sources [3/5] ✅ Fact-checking claims ............... ✓ 18/23 verified [4/5] 🧬 Synthesizing findings .............. [5/5] ✍️ Writing report .................... 📄 Report saved → out/report-20260518-1432.pdf 📊 Run trace → out/trace-20260518-1432.json

Built for serious research

MIT licensed. Ready to extend. Open the repo and start hacking.