Search Packages

superlocalmemory

World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on LoCoMo. No cloud, no APIs, no data leaves your machine. Additionally, mode C (LLM/Cloud) - 87.7% LoCoMo. Research-backed. arXiv: 2603.14588

kalibr

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

self-heal-llm

Automatic repair for failing Python code, powered by any LLM.

agentassert-abc

Formal behavioral specification and runtime enforcement for autonomous AI agents. Agent Behavioral Contracts (ABC).

self-improving-loop

Rollback-first reliability layer for AI agents: trace failures, apply guarded changes, and rollback on regression.

harness0

Layer 0 of agent reliability — the framework-agnostic harness that makes any AI agent stable.

llm-cost-reduction

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

llm-cost-optimizer

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

llama-index-storage-chat-store-superlocalmemory

LlamaIndex chat store backed by SuperLocalMemory V2 — 100% local, zero cloud