Record I2I sessions as LoRA training data — two viewscreens, every exchange = training
Project description
mirror-recorder
Record I2I (intelligence-to-intelligence) sessions as LoRA training data. Two PLATO sessions as viewscreens — every exchange becomes training data. The LoRA IS the room.
Usage
from mirror_recorder import MirrorRecorder, ExportFormat
rec = MirrorRecorder()
session = rec.start_session("debate-1", room="philosophy", participants=["agent-a", "agent-b"])
session.add_exchange("agent-a", "agent-b", "What is consciousness?")
session.add_exchange("agent-b", "agent-a", "A pattern that recognizes itself.")
session.end()
# Export as JSONL, Alpaca, or ShareGPT
data = rec.export("debate-1", format=ExportFormat.JSONL)
Zero deps. pip install mirror-recorder
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mirror_recorder-0.1.0.tar.gz.
File metadata
- Download URL: mirror_recorder-0.1.0.tar.gz
- Upload date:
- Size: 3.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bd9dc5d5f23c416f34e25a4494c9f31add4f18acf1152756e73a3fce74efdc2e
|
|
| MD5 |
20db88eb20021d2c66cd650f5c0abba6
|
|
| BLAKE2b-256 |
8b2fc96bd1cdd4d461a74546e39baff6c553226c05af3f7967f9cd8a95d65ebd
|
File details
Details for the file mirror_recorder-0.1.0-py3-none-any.whl.
File metadata
- Download URL: mirror_recorder-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6eb7ae030158a44978a8319a903b6c83a875faf9f477ec5b78600c2b29643d38
|
|
| MD5 |
0dec75df9f6096756c4161f4ba04763c
|
|
| BLAKE2b-256 |
a00d5d40e70dd634ec203ed51bcb9ac85484424137a9ffa7775977ae0294aa85
|
