It lies. Confidently. ALL THE TIME.
I’m autistic and extremely allergic to vibes-based tooling, so … I built a thing. Maybe it’s useful to you too.
The thing: llama-conductor
llama-conductor is a router that sits between your frontend (eg: OWUI) & backend (llama.cpp + llama-swap). Local-first but it should talk to anything OpenAI-compatible if you point it there (note: experimental so YMMV).
LC is a glass-box that makes the stack behave like a deterministic system, instead of a drunk telling a story about the fish that got away.
TL;DR: “In God we trust. All others must bring data.”
Three examples:
1. KB mechanics (markdown, JSON, checksums)
You keep “knowledge” as dumb folders on disk. Drop docs (.txt, .md, .pdf`) in them. Then:
>>attach <kb> - attaches a KB folder
>>summ new - generates SUMM_.md files with SHA-256 provenance baked in + moves the original to a sub-folder
Now, when you ask something like:
> “yo, what did the Commodore C64 retail for in 1982?”
..it answers from the attached KBs only.
If the fact isn’t there, it tells you - explicitly - instead of winging it. Eg:
"The provided facts state the Commodore 64 launched at $595 and was reduced to $250, but do not specify a 1982 retail price. The Amiga’s pricing and timeline are also not detailed in the given facts.
Missing information includes the exact 1982 retail price for Commodore’s product line and which specific model(s) were sold then."
[Confidence: medium | Source: Mixed]
No vibes. Just: here’s what’s in your docs, here’s what’s missing, don't GIGO yourself into stupid.
Then, if you're happy with the summary, you can:
>>move to vault
2. Mentats: proof-or-refusal mode (Vault-only)
Mentats is the “deep think” pipeline against your curated sources.
* no chat history
* no filesystem KBs
* no Vodka
* Vault-only grounding (Qdrant)
It runs a triple-pass (thinker → critic → thinker). It’s slow on purpose. You can audit it. And if the Vault has nothing relevant? It refuses and tells you to go pound sand:
FINAL_ANSWER:
The provided facts do not contain information about the Acorn computer or its 1995 sale price.
Sources: Vault
FACTS_USED: NONE
[ZARDOZ HATH SPOKEN]
Also yes, it writes a mentats_debug.log. Go look at it any time you want.
The flow is basically:
Attach KBs → SUMM → Move to Vault → Mentats.
No mystery meat. No “trust me bro, embeddings.”
3. Vodka: deterministic memory on a potato budget
Potato PCs have two classic problems: goldfish memory + context bloat that murders your VRAM.
Vodka fixes both without extra model compute.
* !! stores facts verbatim (JSON on disk)
* ?? recalls them verbatim (TTL + touch limits so memory doesn’t become landfill)
* CTC (Cut The Crap)* hard-caps context (last N messages + char cap) and creates a concatenated summary (not LLM) so you don’t get VRAM spikes after 400 messages
So instead of:
“Remember my server is 203.0.113.42” → “Got it!” → [100 msgs later] → “127.0.0.1”
you get:
!! my server is 203.0.113.42` ?? server ip → 203.0.113.42 (with TTL/touch metadata)
And because context stays bounded: stable KV cache, stable speed, your potato PC stops crying.
There’s more (a lot more) in the README, but I’ve already over-autism’ed this post.
TL;DR:
If you want your local LLM to shut up when it doesn’t know and show receipts when it does, come poke it:
Primary (Codeberg) https://codeberg.org/BobbyLLM/llama-conductor
Mirror (GitHub): https://github.com/BobbyLLM/llama-conductor
PS: Sorry about the AI slop image. I can't draw for shit.
PPS: A human with ASD wrote this using Notepad++. If it the formatting or language are weird, now you know why.
gogopromptless•2w ago
BobbyLLM•2w ago
Do you mean generally though - how many facts does it extract from a typical document of X length? Or do you mean what my own personal corpus currently is?
gogopromptless•2w ago
My crappy personal system is a telegram channel "Today I Learned" that grows at roughly 5 messages per day. The search is obviously much worse than your tool.
The design of no rewrites for facts storage was an approach I have not seen from any of my friends' agent memory setups, so that difference struck my curiosity for how well its working in practice.
BobbyLLM•2w ago
If you're talking about the "Fastrecall" part of it, it's clamped to around 3000 entries. Beyond that...I mean...it's just a JSON file. How much do you hate yourself? lol :)
I use mine as intended (well, by me) as a short term memory store with a TTL of 14 days. Right now it has...350ish stored facts with different expiration dates. You can play around with the settings and max resets (touches), but if ctx > max_items, janitor rolls in and the oldest get pruned anyway.
If you're talking about the chat bloat control part (cut the crap), I set mine to keep the last 2 user/assistant pairs and a soft cap of 2000 characters. That middle part obviously decays during the chat. I like to keep my chatty fast.
If you're asking about the KB (attach) system: generally speaking, the SUMM function seems to generate a summary of upto about 1500 characters. That's what...250 words? Short and sweet...because again, potato pc + smart grep = don't be stupid.
In theory, the KB thing is limited by you SSD and pain tolerance. I have about 1500 items I query against and it's still in the sub-secondish range.
Mentats / vault? Scales via Qdrant.
Does that answer it? None of this shit is enterprise grade; it's purely for personal use.