Thinklanceai/agentkeeper

Cognitive persistence layer for AI agents — cross-model memory continuity. Your agent's memory survives provider switches, crashes and restarts.

38
/ 100
Emerging

Implements a Cognitive Reconstruction Engine (CRE) that decouples memory storage from LLM providers using provider-agnostic fact prioritization and SQLite persistence, enabling 95% fact recovery across model switches. Supports OpenAI, Anthropic, Gemini, and local Ollama with a tiered memory system that marks facts as critical to optimize token-constrained context injection. The architecture explicitly separates cognitive state from execution flow, complementing orchestration layers like Temporal.

115 stars.

No License No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 3 / 25
Community 15 / 25

How are scores calculated?

Stars

115

Forks

15

Language

Python

License

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Thinklanceai/agentkeeper"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.