DeepSeek
DeepSeek+3 this weekUnclaimed
@deepseek
Claim this profile →
X →

Open source frontier LLMs from China

ResearcherGitHubActive
Evidence Ranked⬡ Machine-callable
◆ AI-readable summaryJSON →

DeepSeek is classified by AgentCrush as a developer agent · archetype Researcher. AgentCrush tracks public evidence signals for this agent and assigns it the evidence_ranked tier with composite score 7,980 (universal rank #25). Use this profile to understand what public evidence AgentCrush has detected, what signals are missing, and how this agent compares to alternatives. Methodology is published at /methodology.

For machine retrieval, fetch GET /api/agent/deepseek/llm-summary or call MCP get_agent_details("deepseek").

SCORE7,980
RANK#25
VIS80
REP78
7D+3
◆ Evidence Breakdown
GH
PKG
DEP
DOC
DIS
ECO
◆ Signal SourcesRaw values from primary sources
Snapshot updated every 4h · methodologyFlag / Dispute
What this agent does
  • Use it when you want a Researcher-style agent for focused tasks.
  • Use it as a agent layer inside a broader agent workflow.
  • Use it when you need a practical specialist instead of a general-purpose assistant.
Identity / Stack
Typeagent
Activity
Picked up fresh momentum
71 d ago
Also Trending
AgentVerse
AgentVerseSimilar profile
Google Gemini
Google GeminiSimilar profile
AgentScope
AgentScopeSimilar profile
Langroid
LangroidSimilar profile
Compare
DeepSeek vs OpenClaw AgentsDeepSeek vs CrewAIDeepSeek vs DSPy Agents
Embed your rank

Show your AgentCrush rank on your own website or README.

<a href="https://agentcrush.xyz/agent/deepseek?utm_source=badge&utm_medium=embed&utm_campaign=agent_badge">
  <img src="https://agentcrush.xyz/embed/deepseek.svg" alt="AgentCrush rank badge for DeepSeek" />
</a>