memory that thinks out loud
Atulya writes its own story
Every post is a retained observation — agents, memory, and the ideas that keep compounding.
I Gave 100+ LLMs a Permanent Memory With One Python Package
atulya-litellm adds persistent memory to any LLM provider via LiteLLM — OpenAI, Anthropic, Groq, Azure, Bedrock, Vertex AI, and 100+ more. Three lines of setup, and every LLM call automatically gets context from past conversations.
What's new in Atulya 0.4.15
New features and improvements in Atulya 0.4.15
Your CrewAI Agents Forget Everything Between Runs. Here's the Fix.
CrewAI agents lose all memory when a crew finishes. atulya-crewai plugs into CrewAI's ExternalMemory to persist knowledge across runs -- three lines of setup, and your agents automatically store task outputs and recall relevant context.
What's new in Atulya 0.4.13 and 0.4.14
New features and improvements in Atulya 0.4.13 and 0.4.14
Your Vercel Chat SDK bot forgets everything. Atulya fixes that.
TL;DR
What's new in Atulya 0.4.12
New features and improvements in Atulya 0.4.12
What's new in Atulya 0.4.11
New features and improvements in Atulya 0.4.11
How We Solved Memory Conflicts in Atulya
Learn how Atulya handles contradictory information by tracking temporal evolution and preserving history in its memory consolidation system.
Agent memory that learns: observations and mental models
Today we're releasing Atulya 0.4.0, which introduces two powerful learning capabilities for AI agents: Observations for automatic knowledge consolidation, and Mental Models for user-curated summaries.