#llm

LatentGate — Local-First AI Compression

KathanModh259

Compress images, text, conversations, and documents locally via Ollama before sending to cloud LLMs. Save ~80% on token costs.

AI Context Copier

sacro

Your AI tells you exactly which files it needs. AI Context Copier gets them into your clipboard in one click — no manual opening, no tab switching, no repetition.

Doctopus.ai

Doctopus-ai

Fan a prompt out to multiple AI coding tools, get one verified best answer, and train the router via implicit feedback from your editor.

Quorum — Multi-LLM Consensus (Pro)

sovereignchain

Run a single prompt across 14+ frontier LLMs (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Cohere, NVIDIA) from VS Code. Tamper-evident traceability log, semantic agreement scoring, BYOK. Requires Pro license.

Azure DevOps Build AI Analyzer

ai-build-analyzer

Analyzes failed pipeline runs with your own OpenAI-compatible LLM (local or hosted): a pipeline task produces the analysis and a build results tab displays it.

Leebox

leeb

Leebox - AI chat panel powered by OpenRouter.

Fermi

fermi

AI coding agent for long sessions — right in your editor

Microfix

Microfix

Surgical AI error fixer – only fixes exact lines, verified by real linter

AI Debrief

ArkaprabhaChowdhury

Understand AI-written code while you build.

Copilot Optimizer AI

morten-ln

Get better Copilot answers automatically. Fix prompts. Improve answers. Learn over time.

CleanMyPrompt — AI Security & Token Intelligence

cleanmyprompt

Stop leaking secrets. Stop burning tokens. Intercepts API keys, PII & credentials before they reach Copilot, and compresses code with LSP-aware squeeze to cut token costs by 30–70%. 100% local.

Dify DSL Visualizer

real-akimoto-akira

Visualize and edit Dify app DSL (workflow / chatflow) YAML files as an interactive graph inside VS Code.