中文
~/home / TypeScript / GitHub
GitHub · TypeScript

openclaude

openclaude is a coding AI agent for To autonomously invoke Claude models for code generation, refactoring, and debugging in offline or privacy-sensitive environments. Pricing: Free. As of 2026-10-22, KanonAgent records 34.1k upvotes. First indexed by KanonAgent on 2026-09-29.
A locally-run Claude AI agent that lets developers deploy and use Claude models offline, giving them full control over data and performance without relying on the cloud.
openclaude — official preview image
34.1k upvotes
Tracked by Kanon since Sep 29, 2026
Cooling
status
50/100
momentum · conf 0.92
61d
tracked since 2026-08-22
2026-10-20
last meaningful change
6
evidence records

Status basis: npm_downloads_7d momentum fell to -5383 per 3d from 183 (<= 40% of the prior window)

📈 Timelinewhat changed, and when
🔎 Known / Unknown 10 of 23 fields unknown
Machine-callable— unknown —
Open source1 verified 1 quote(s)
Self-hostable1 inferred 1 quote(s)
Bring your own key1 inferred —
Autonomy level2 inferred 1 quote(s)
Pricing model— unknown —
Integrationsmcp,github inferred 2 quote(s)

“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.

🤖 Agent teardown · coding
Job to be doneTo autonomously invoke Claude models for code generation, refactoring, and debugging in offline or privacy-sensitive environments.
AutonomyL2 · tool-calling(evidence: "prompts, tools, agents, MCP, slash commands, and streaming o…")
Who it is forDevelopers
Prerequisitesopen source · self-hostable · bring your own API key
Integrationsmcp · github
PricingFree
Traction · why it is rising33,571 votes on ProductHunt highlight strong community demand for local AI tools.
Why it matters

It delivers high privacy and low latency AI coding assistance by running Claude models entirely on-device, making it a practical example of AI agents in edge computing scenarios.

Evidence quotesverbatim, from the product’s own materials

“public GitHub repository (README fetched)”— structural
“OpenClaude is an open-source coding-agent CLI for cloud and local model providers.”— readme
“prompts, tools, agents, MCP, slash commands, and streaming output.”— readme
“Use OpenAI-compatible APIs, Gemini, GitHub Models, Codex OAuth, Codex, Ollama, Atomic Chat”— readme
TypeScript
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
openclaude badge
Building openclaude? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
Share on X
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.

FAQ

What is openclaude?

A locally-run Claude AI agent that lets developers deploy and use Claude models offline, giving them full control over data and performance without relying on the cloud.

What does openclaude do?

To autonomously invoke Claude models for code generation, refactoring, and debugging in offline or privacy-sensitive environments.

Why does openclaude matter?

It delivers high privacy and low latency AI coding assistance by running Claude models entirely on-device, making it a practical example of AI agents in edge computing scenarios.

How much does openclaude cost?

Free

Is openclaude free?

Yes — openclaude has a free tier. Pricing as stated on its own page: Free

Is openclaude open source?

Yes — openclaude is open source.

Can I self-host openclaude?

Yes — openclaude can be self-hosted.

What does openclaude integrate with?

mcp,github

How popular is openclaude?

As tracked by KanonAgent: 34.1k upvotes (first indexed 2026-09-29).

What are the best openclaude alternatives?

Similar AI agents tracked by KanonAgent: deepseek-harness, gemini-cli, Codédex, LLM Gateway, oh-my-openagent, goose.

openclaude alternatives — similar AI agents

deepseek-harnessgemini-cliCodédexLLM Gatewayoh-my-openagentgoose

Where this fits — browse the same shelf

AI Coding AgentsAI agents for Code generation and debuggingAre there open-source AI agents for Code generation and debugging?Can I self-host an AI agent for Code generation and debugging?AI agents that work with MCP (Model Context Protocol)AI agents that work with GitHub