Thinklanceai/agentkeeper
Cognitive persistence layer for AI agents — cross-model memory continuity. Your agent's memory survives provider switches, crashes and restarts.
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.
Stars
115
Forks
15
Language
Python
License
—
Category
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.
Featured in
Higher-rated alternatives
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
MemMachine/MemMachine
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory...
knowns-dev/knowns
The memory layer for AI-native development — giving AI persistent understanding of your software...
Dicklesworthstone/cass_memory_system
Procedural memory for AI coding agents: transforms scattered session history into persistent,...
rexdivakar/HippocampAI
HippocampAI — Autonomous Memory Engine for LLM Agents