imp
Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.
Open the source (opens github.com) https://github.com/kekzl/imp
What it is
Agents & frameworks from kekzl.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Get the code
git clone https://github.com/kekzl/imp.git
Standard git access to a public repository
Setup steps: not provided by the source. Follow the instructions on the source.
Related
-
Flide
Agents & frameworks🔥🔥 The extremely fast inference engine for decision model
git clone https://github.com/OmniJev/Flide.git -
ai-hardware-engineer-roadmap
Agents & frameworksMaster AI inference, AI agent harness systems, and hardware engineering — then design a physical AI chip. That is the goal.
git clone https://github.com/ai-hpc/ai-hardware-engineer-roadmap.git -
Browser Use
Agents & frameworksA Python library that lets an AI agent use a web browser to finish tasks.
uv add browser-use -
Raven
Agents & frameworksThe Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
git clone https://github.com/EverMind-AI/Raven.git -
claude-smart
Agents & frameworksTurns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
git clone https://github.com/ReflexioAI/claude-smart.git -
letta
Agents & frameworksPlatform for stateful agents: AI with advanced memory that can learn and self-improve over time.
git clone https://github.com/letta-ai/letta.git