CLM vs strands-decider
Contrastive Language Models: CLM-8B, an open System-1 decision model scoring states against actions — typed choice/score/yes-no answers on a TypeSafe-compatible API, up to 9x faster than Jev. — versus — Strands' small decision model (2B, Qwen3.5-based): pick between options, answer yes/no or rate on a scale with calibrated confidence. CLI and /v1/systemone server on CUDA, MPS, MLX or CPU.
Both serve Jev-style typed decisions from open weights; CLM is an 8B contrastive state-action ranker, strands-decider a 2B model you can run on CPU or MLX.
| CLM | strands-decider | |
|---|---|---|
| Stars | 3.0k | 579 |
| Forks | 256 | 77 |
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | 6 days ago | 2 days ago |
| Topics | decision-models, local | decision-models, local |
| Curated connections | 6 | 5 |
CLM — the curator's take
Use it when an agent must pick among many candidates fast — next action, tool, best-of-N verifier — and you want calibrated probabilities on your own GPU; cached state/action embeddings are why it beats Jev on latency. Not for anything generative: it ranks, never writes. Needs a Qwen3-8B encoder under vLLM plus the head, and states past 2,048 tokens are truncated unless you raise both limits.
strands-decider — the curator's take
Use it for the many small judgments inside an agent workflow — routing, triage, urgency, sentiment — where an LLM call is too slow and training a classifier too much work; answers at ≥0.9 confidence were right ~95% of the time on unseen tasks, so threshold and escalate the rest. It decides, never writes. At 2B it runs on a laptop; for agent-action ranking at scale, CLM's cached-embedding design is faster.