DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run a chat that remembers facts across turns with MemT 1 0

Serve MemT-1.0-Nano with SGLang and chat with native memory that is kept after each reply.

  • Top pick
  • Research
  • Advanced
  • 2 hours
  • From the README
  • Any agent

Who it is forAn ML engineer with a Linux GPU server who wants to test whether a model can keep user facts in its own memory instead of a long transcript.

The problemLong chat transcripts grow costly, and it is hard to tell whether a model retains earlier facts without resending the full context.

The outcomeA running SGLang server and a Python session where facts from earlier turns, such as a pet's name and age, are answered correctly after the plaintext context is cleared.

What you need first

  • Linux server with NVIDIA CUDA and Python 3.11 or newer
  • uv installed for the inference install step
  • A complete local MemT-1.0-Nano checkpoint with BF16 weights, configuration and tokenizer assets
  • Two GPUs for the Nano example in the README
  • Write access to ./memt-state on the server for memory snapshots

Steps

  1. Run cd inference in a clone of the MemTensor/MemT-1.0 repository.
  2. Run uv pip install '.[server]' on the Linux GPU server.
  3. Run sh start_memt_nano.sh /models/MemT-1.0-Nano and keep it running; it serves at http://127.0.0.1:30000.
  4. In another terminal, run the Python connection code from the Quick Start, pointing model_path at the same checkpoint.
  5. Call session.chat(..., enable_memory=True) with a fact in one turn, then ask a follow-up question that depends on that fact. (inferred, check the README)

Prompt for your agent

Use the MemTensor/MemT-1.0 repo to start the MemT-1.0-Nano server from /models/<checkpoint-folder> and run the Quick Start chat example. Expected output: a reply that restates the kitten name, age and favorite food from earlier turns. Verify that the answer names facts that were given only in the first message.

Caveat. The README requires a complete local checkpoint and a CUDA GPU setup, and it notes that the sample replies are illustrative rather than guaranteed output.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page