Alternatives to mini-AGI

These tools sit near mini-AGI. Compare features and pricing before you switch.

Alternatives

Bespoke Nimble: another small, self-hostable model, but trained for structured decisions rather than continual learning.
LFM2.5 2.6B: a small open-weight model you can actually run today for practical work.
LongCat 2.0: a much larger open model to compare on long-context behaviour.

Bespoke Labs' open-weight 9B model and training recipe that turn Jev-style decisions into single-token choices with probabilities, runnable locally.

—DR: —AS: —

Liquid AI's open-weight 2.6B dense model trained for on-device agentic workloads, with 128K context and native tool calling.

500000DR: 70AS: 72

Meituan's open-weight MoE model: 1.6T total / ~48B active params, 1M context, MIT. Strong on coding and agentic tasks (2026-08-25).

—DR: —AS: —