Interlens: Framework for Multi-Agent Interaction and Interpretability

This library provides a harness, optimized utilities, and interpretability hooks for multi-agent conversation rollouts.

A harness for multi-agent (model-to-model) conversations with first-class interpretability—activation capture, steering, activation patching, and token logprobs—all hooked into the same generation path as real turns and tagged to conversation structure. Scales from one interactive dialogue to thousands of checkpointed, multi-GPU rollouts.

from interlens import Conversation

conv = Conversation.from_models(
    ("Qwen/Qwen2.5-0.5B-Instruct", "Qwen/Qwen2.5-0.5B-Instruct"), names=("alice", "bob"),
    shared_context="Let's debate: is cereal a soup?",
)
conv.run(turns=4, first="alice")
print(conv.transcript)

See docs/examples for sample code.

*Documentation for LLMs!

Install

pip install interlens
# with hosted-API participants (APIParticipant):
pip install "interlens[api]"

PyTorch / CUDA note

torch is declared as a plain, build-agnostic dependency — install the wheel matching your platform (CUDA / CPU / MPS) before or alongside interlens. E.g. for CUDA 13.0:

pip install torch --index-url https://download.pytorch.org/whl/cu130

See https://pytorch.org/get-started/locally/.

What's inside

  • Conversation — turn-taking over a shared, perspective-neutral Transcript; per-speaker view pipeline (system/private framing → context-fit → family-correct chat template).
  • AutoModelParticipant — HF-style factory (from_pretrained / from_model / from_) that returns the family-correct participant (Qwen/Gemma/…); APIParticipant for hosted models.
  • Interpretability — conv.capture(...), SteeringSpec, Patch, token_logprobs, backed by a queryable ActivationCache.
  • Scale — conv.rollout(...) / interlens.run([...]): multi-GPU, checkpointed, resumable, batched co-stepping, with in-worker analyzer callbacks; data-driven rollouts via dataset_field, matched compute via TokenBudget.
  • One object, no ceremony — a Conversation (with lazy participants) is at once the serializable recipe, the live dialogue, and the rollout driver; build it functionally (.turns(6).data(ds).analyzer(grade)), .set(...) copy-on-write, and save/load (recipe + transcript).

See docs/examples/ for a simple→advanced walkthrough of the whole API.

Develop

git clone https://github.com/Sid-MB/interlens && cd interlens
uv sync                     # installs the package + dev group (pytest, pre-commit)
uv run pre-commit install   # one-time: activate the AGPLv3 license-header git hook
uv run pytest               
# fast tests; opt-in to thorough tests requiring downloading models + a GPU with: pytest -m slow

License

GNU AGPLv3 — see LICENSE.

Project links

Data verified by PyPI on Jul 27, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.1.74)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for smb from gravatar.com smb

Credits

Author: Siddharth M. Bhatia

GitHub Statistics

Data verified by PyPI on Jul 27, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

AGPL-3.0-only

Requires

Python <3.14, >=3.11

Provides Extra

api benchmarks inspect

Tags

activation-steering interpretability llm multi-agent transformers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

interlens-0.1.33.tar.gz (324.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

interlens-0.1.33-py3-none-any.whl (435.4 kB view details)

Uploaded Python 3

File details

Details for the file interlens-0.1.33.tar.gz.

File metadata

  • Download URL: interlens-0.1.33.tar.gz
  • Upload date:
  • Size: 324.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for interlens-0.1.33.tar.gz
Algorithm Hash digest
SHA256 072c3b6a8738211e720f358c6867e560c00feaf3fc84941b06812545f0bc3dfe
MD5 0c763dbb499546b187b441d203da583e
BLAKE2b-256 641af6109f4d2402d930af0f457585e406dd7cac2e113a8a7aa4b81db1f8631f

See more details on using hashes here.

Provenance

The following attestation bundles were made for interlens-0.1.33.tar.gz:

Publisher: publish.yml on Sid-MB/interlens

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file interlens-0.1.33-py3-none-any.whl.

File metadata

  • Download URL: interlens-0.1.33-py3-none-any.whl
  • Upload date:
  • Size: 435.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for interlens-0.1.33-py3-none-any.whl
Algorithm Hash digest
SHA256 e1ef1fdb1ee40c72ff4d4b7818f8cb9f995367b77eec6ea58f3549a7dfbf3c81
MD5 2ee7ab0ad70e10c58a761de0a88b612f
BLAKE2b-256 d1432902e2b1d225206c0466e9a4a5d2be8cb85d4c45538830a8d66a0450bfb8

See more details on using hashes here.

Provenance

The following attestation bundles were made for interlens-0.1.33-py3-none-any.whl:

Publisher: publish.yml on Sid-MB/interlens

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.1.74

2 files

0.1.73

2 files

0.1.72

2 files

0.1.71

2 files

0.1.70

2 files

0.1.69

2 files

0.1.67

2 files

0.1.66

2 files

0.1.65

2 files

0.1.64

2 files

0.1.63

2 files

0.1.62

2 files

0.1.61

2 files

0.1.60

2 files

0.1.59

2 files

0.1.58

2 files

0.1.57

2 files

0.1.56

2 files

0.1.55

2 files

0.1.54

2 files

0.1.53

2 files

0.1.52

2 files

0.1.51

2 files

0.1.50

2 files

0.1.49

2 files

0.1.48

2 files

0.1.47

2 files

0.1.46

2 files

0.1.45

2 files

0.1.44

2 files

0.1.43

2 files

0.1.42

2 files

0.1.41

2 files

0.1.40

2 files

0.1.39

2 files

0.1.38

2 files

0.1.37

2 files

0.1.36

2 files

0.1.35

2 files

0.1.34

2 files

This release

0.1.33 This release

2 files

0.1.32

2 files

0.1.31

2 files

0.1.30

2 files

0.1.29

2 files

0.1.28

2 files

0.1.27

2 files

0.1.26

2 files

0.1.25

2 files

0.1.24

2 files

0.1.23

2 files

0.1.22

2 files

0.1.21

2 files

0.1.20

2 files

0.1.19

2 files

0.1.18

2 files

0.1.17

2 files

0.1.16

2 files

0.1.15

2 files

0.1.14

2 files

0.1.13

2 files

0.1.12

2 files

0.1.11

2 files

0.1.10

2 files

0.1.9

2 files

0.1.8

2 files

0.1.7

2 files

0.1.6

2 files

0.1.5

2 files

0.1.4

2 files

0.1.3

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page