Skip to content
ADE Index

Cline vs Dirac vs Reflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG)

Up to four tools, row by row. We do not guess: a cell we have not checked says so.

How they differ

Dirac is a fork of Cline: Dirac is a fork of Cline. github.com

Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

Checked for Cline and Dirac, not yet for Reflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG): Price (Cline: ; Dirac: ), Model providers (Cline: , , , , , SpaceXSI (Grok), , Amazon Bedrock, , Moonshot AI, , Z.ai, , , , , , , , , , Alibaba (Qwen), , , , Nebius Token Factory (Nebius AI Studio), , , , , , CoreWeave (Weights & Biases), , , , , , , , , , , , , Text Generation Inference (TGI), Ask Sage, , , , ; Dirac: , , , , SpaceXSI (Grok), , , , Moonshot AI, , Z.ai, , , , , Together AI, , , , Alibaba (Qwen), , , Nebius Token Factory (Nebius AI Studio), , , Volcengine, CoreWeave (Weights & Biases), , , Nous Research, , UnbiasedAI), Bring your own key (Cline: ; Dirac: )

Not yet checked for any of these tools: agents it runs, editors and systems.

Provider names use the same listing as each tool page. Dotted values open their quote. A capability not shown is not yet checked; the tool may still have it.

About these tools

Cline

Dirac

How to read the Index score

At a glance

Index score out of 100

Cline41Dirac21Reflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG)Not enough data yet

Mindshare HN mentions, 90 days

Cline41Dirac6Reflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG)0

Adoption GitHub stars, not scored

Cline71.7kDirac1.6kReflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG)No public repository

Release days last 90 days

Cline30Dirac23Reflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG)Not yet checked

Lowest monthly plan billed monthly, lower is cheaper

Cline$9.99/monthDiracNot yet checkedReflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG)Not yet checked

Platforms listed surfaces

Cline4DiracNot yet checkedReflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG)1

Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. After activation, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built

Differences only
3 of 4
ClineCline Bot Inc. · IDE extension
Diracdirac-run · IDE extension
Interface
Cline desktop app: sessions list and a finished task with command output and summary
Dirac interface
What it is
Editor coding agent with provider API keys and local model support
Coding agent for VS Code, the terminal and ACP-compatible clients
Local-model coding assistant with approval-based agent edits and commands
Category
IDE extensionCline family
IDE extension
IDE extension
Pricing
Starts at (billing shown)
Not yet checked
Lowest monthly plan
Not yet checked
Not yet checked
Free tier
Not yet checked
Plans
Not yet checked
Bring your own key
Yes
Yes
Not yet checked
Runs on
JetBrains
Yes
Not yet checked
Not yet checked
Neovim
Yes
Not yet checked
Not yet checked
Terminal
Yes
Not yet checked
Not yet checked
VS Code
Yes
Not yet checked
Yes
Models and agents
Model providers
OpenAIAnthropicOpenRouterGoogleOllamaSpaceXSI (Grok)DeepSeekAmazon Bedrock
+42 more model providers
LM StudioMoonshot AIGroqZ.aiMistralFireworksMiniMaxTogether AIvLLMAzure OpenAIHugging FaceVercel AI GatewayCerebrasAlibaba (Qwen)XiaomiBasetenLiteLLMNebius Token Factory (Nebius AI Studio)PerplexityRequestySambaNovaVolcengineChutesCoreWeave (Weights & Biases)Atomic ChatPoolsideCrusoeai&AIHubMixTencentClinePassv0 APIAnyscaleAvianHuawei CloudNous ResearchText Generation Inference (TGI)Ask SageDifySAP AI CoreClineHicap
+ providers you addNot every provider checked yet
OpenAIAnthropicOpenRouterGoogleSpaceXSI (Grok)DeepSeekAmazon BedrockLM Studio
+24 more model providers
Moonshot AIGroqZ.aiMistralFireworksMiniMaxGitHub CopilotTogether AIHugging FaceVercel AI GatewayCerebrasAlibaba (Qwen)BasetenLiteLLMNebius Token Factory (Nebius AI Studio)RequestySambaNovaVolcengineCoreWeave (Weights & Biases)AIHubMixHuawei CloudNous ResearchDifyUnbiasedAI
+ providers you addNot every provider checked yet
Not yet checked
Models
OpenAI-compatible
AWS BedrockGoogle Cloud Vertex AI
Not yet checked
Drives these agents
Not yet checked
Not yet checked
Not yet checked
Source and activity
Source
Not yet checked
GitHub stars
Most
No public repository
Release days, last 90 days
30Most
23
Not yet checked
Release days per week
Not yet checked
Latest release, any channel
v4.1.26 26 Oct 2026
v0.6.1 17 Nov 2026
Not yet checked
Index score
Score and rank
41 #24 Score 40.6; ranked on the unrounded score
21 #70 Score 21.1; ranked on the unrounded score
Not enough data yet
Mindshare
4141 Hacker News mentions in the last 90 days
216 Hacker News mentions in the last 90 days
00 Hacker News mentions in the last 90 days
Adoption, not scored
9271,731 stars, read 18 Nov 2026
601,559 stars, read 18 Nov 2026
No public repository
Votes
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Not ranked
Full page

Watch Cline vs Dirac vs Reflexor: Local AI Coding Assistant & Agent (Ollama, DeepSeek, LLM, RAG) on YouTube

More comparisons

Build your own