Open the persistent console, keep talking, and say “try again” to resume a saved task.
LOLM by Qira · Open source · Runs locally
Local intelligence, under your control.
LOLM is Qira’s local AI agent. Ask it to work with files, write code, or check a project on your computer. Connect your chosen model, start with a small task, and inspect what it produces.
The local CLI does not require a Qira account. This website explains setup; work runs on your computer.
● Ollama local · qwen3:14b ◆ NFET active Talk normally. I remember this session. YOU Make me a PDF launch plan and put it on my Desktop LOLM Researching and writing your document… ◆ Checking the result Created /Users/you/Desktop/lolm-document.pdf YOU _
Use your existing provider, Ollama, or any OpenAI-compatible endpoint.
Files and commands run locally. Remote providers receive only the inference context you choose to send.
How the agent keeps its bearings.
LOLM can keep task state across sessions and check its work before continuing. Its optional NFET research components explore signals for when to retrieve context, verify, branch, or finish. Availability depends on your local setup; see the installation and research notes.
stateₜ = [ corrected_hidden, entropy, drift, gate, regime ]
control → continue · retrieve · verify · branch · finalize
control → continue · retrieve · verify · branch · finalize
Use the model you already trust.
OpenAIAnthropicGeminixAIOpenRouterGroqMistralDeepSeekTogetherCerebrasOllamaCustom