The models log uses
log uses six models. Two run on your own machine, with no key and no internet once they are downloaded. Four are hosted services you add a key for. This page says what each one does, what your machine needs, and how the indexes they read are built.
At a glance
| Model | Runs | What it does in log | Size | Key |
|---|---|---|---|---|
| all-MiniLM-L6-v2 (8-bit) | your machine | turns text into meaning vectors: log search, your voice index, the knowledge base, matching what you typed to a play, and (with char n-grams) the voice gate's AI-conventions detector trained on you | 23 MB | none |
| roberta-base-go_emotions (8-bit) | your machine | the top three emotions of each new message someone sends you, a feature of who they are and where they are (pipeline labels) | 125 MB | none |
| LFM2.5-VL-450M (4-bit) | your machine | describes every picture, gif and video frame someone sends you, as text | 352 MB | none |
SubQ subq-snap-1.1 | hosted | the voice gate (does a draft sound like you), reading an unknown page state, briefs, meme taste | n/a | SUBQ_API_KEY |
Jina jina-embeddings-v5-omni-small and jina-reranker-v3.5 | hosted | ranking a chat's history for the voice gate, and the old AI tells index (read only with LOG_AI_TELLS=jina) | n/a | JINA_API_KEY |
| AssemblyAI | hosted | what was said in a voice note or a video | n/a | ASSEMBLYAI_API_KEY |
Inworld inworld-tts-2 (or Fish Audio s2.1-pro) | hosted | speaks a voice note in your cloned voice, only when you ask | n/a | INWORLD_API_KEY or FISH_API_KEY |
The model names are in the code, so this table can be checked against it: EMBED_MODEL (src/search/conversations/types.ts), VISION_MODEL (src/media/describer/types.ts), VOICE_MODEL (src/twitter/copy/voice/types.ts), JINA_EMBED_MODEL and JINA_RERANK_MODEL (src/voice/aiTells/types.ts), and the voice providers in src/extensions/inworld and src/extensions/fishAudio.
Where each one sits
Without the hosted keys, log still reads, searches and describes pictures. The voice gate, transcripts and voice notes need their keys.
What your machine needs
Measured on this project's own machine on 2026-11-09 (Windows 11, 16 threads, CPU only, no GPU):
| Load | Each use | Memory | |
|---|---|---|---|
| MiniLM | 0.17 s | 2.8 ms p50, 9.8 ms p95 to embed one message (20 runs) | small, inside the process using it |
| go_emotions RoBERTa | 1.3 s | 24 ms p50, 35 ms p95 per message on a quiet machine; run after the who and where labels so it never holds the push | inside the push process |
| LFM2.5-VL | 5.7 s | 6.3 to 7.4 s per picture (3 runs) | peaked at 1.25 GB |
| The describer idle, between pictures | n/a | n/a | about 100 MB |
So, at least:
- A 64-bit machine. Both local models run on the CPU, so no GPU is needed.
- About 2 GB of free memory for the picture model while it works. It stops itself, loudly, past 4 GB (
MEMORY_CEILING_MB), and only one describer runs per machine. - About 400 MB of disk for the two models. They download once, the first time they are needed, into
node_modules/@huggingface/transformers/.cache. - ffmpeg and ffprobe on your PATH, for videos and voice notes (
LOG_FFMPEGandLOG_FFPROBEpoint elsewhere). - Bun and Python 3.12. The installer sets both up (install).
log voice trainalso needs scikit-learn in that Python (uv pip install --python <LOG_PYTHON> "scikit-learn>=1.5,<2"); without it the trainer runs throughuv run --with scikit-learn.
A picture takes seconds to describe, so pictures queue (at most 20) and are described one at a time. Until one is described it shows as [picture … not described yet], so nobody answers it blind.
How the indexes are built
Every index is built from what is already in log.db or what log has saved, and each one is rebuilt in full by its command. Run them in this order on a new machine:
log search indexreads every conversation once through each platform's own session and builds two indexes in~/.logCli/search: one by keyword (BM25) and one by meaning (MiniLM vectors, searched with HNSW). After that, each new read adds only what changed.log search "<query>"uses both and merges the results.log voice indexbuilds your voice from the conversations step 1 saved: each of your replies paired with what was said just before it, embedded with MiniLM, plus a profile per chat, person and platform. It reads nothing new.log voice trainbuilds the voice gate's AI-conventions detector: your own messages inlog.dbagainst the drafts agents wrote for your chats (read from the agent's sessions and from every draft the gate grades, kept inlog.db), plus, with--fresh <n>, drafts from several frontier models for your real past moments, each beside what you really said (it prints the cost first and stops at--spend, $3 by default). It keeps the words and habits models use and you don't, each beside your nearest real phrasing, and a small classifier head (char n-grams plus MiniLM, fitted with scikit-learn inLOG_PYTHON, applied in TypeScript), with one line per message length so 95% of your own held-out messages pass. The voice gate starts it in the background when it is missing or older than step 2.log voice aiIndexbuilds the old Jina phrase index, read only withLOG_AI_TELLS=jina.log kb sync(optional) puts the rules, skills, docs and agent memory into the knowledge base on Redis, searched the same two ways.
Pictures and videos are not indexed by a command. The describer (log media describer, started by the inbox hook) describes each one as it arrives, and its text is searchable like any message. log media status shows the queue.
The voice gate's embeddings are made once and kept in log.db by the text's hash and model, so each send only embeds what is new. An index made with a different model is rebuilt.
Why these models
- Small enough to run on any machine. MiniLM and LFM2.5-VL run on a CPU, so reading, searching and describing never need the internet or a key.
- Text for every model. Every picture, voice note and video becomes text when it arrives (how it works), so an agent whose model can't see images still knows what was sent.
- Hosted only where it pays. The voice gate and transcripts are worth a hosted model, and each one's balance is in
log balance.