Teams of Agents Shouldn't Repeat Each Other's Mistakes
Multiple agent teams contradict each other and rediscover the same bugs without shared memory. A shared knowledge base keeps every team aligned and coherent.
Every Commit Tells You What Changed. Now Your Agent Knows Why.
CommitContext captures the reasoning behind every commit — decisions, debugging paths, and gotchas — so your agent can investigate issues and connect code.
Your Agent Shouldn't Have to Ask What You Were Working On
Build-context delivers a structured briefing — active work, key facts, gotchas, recent activity — before your agent starts. One command. No cold starts.
Your Agent Now Finds What It Missed Before
MemNexus search now follows connections between memories — entities, facts, topics — not just similar words. 90% recall, stale results filtered by default.
One Command to Connect MemNexus to All Your AI Agents
mx setup auto-detects your AI agents and configures MemNexus across Claude Code, Copilot, Cursor, and more. No external binary, no secrets in config files.
Memory Digest Now Scales to Hundreds of Memories
Recursive digest synthesis partitions large memory sets into focused groups, synthesizes each at full fidelity, and merges into one comprehensive briefing.
Your AI Agent Keeps Missing Half the Story. We Fixed That.
Memory Digest assembles complete project briefings in one command. Gathers up to 100 memories, expands via topic and entity graphs, and synthesizes with LLM.
Some Memories Deserve a Name
Named memories let you assign meaningful names to your most important memories. Updates auto-create versioned chains with full history preserved.
We Taught MemNexus to Read Between the Lines
MemNexus now auto-extracts topics, facts, and entities from your memories using LLM analysis. Richer metadata, more retrieval paths, same search speed.
Fetch Multiple Memories in One Call: Batch Retrieval is Here
MemNexus CLI v1.7.29 introduces batch memory retrieval: fetch multiple memories in a single API call with piping support from search.
Find What You Actually Worked On: Conversation-Based Memory Retrieval
New conversation-based memory retrieval helps developers find work sessions, not just individual memories. Filter by time, group search results by conversation.
Precision Search: Include What You Want, Exclude What You Don't
Introducing --exclude-topics: the complement to topic filtering that gives you complete control over your memory search results.
Why Your AI Keeps Forgetting (And How to Fix It)
Most AI memory is a jumbled pile of everything you've ever said. MemNexus introduces memory versioning and instant recaps to fix the fundamental problems with AI memory.
Stop Playing Detective: How Timeline Search Transforms Memory Reconstruction
Timeline Search optimizes memory retrieval for temporal understanding — reconstruct debugging sessions, review decisions, and brief teammates in one query.
Why Your AI's Memory Is Lying to You (And How We Fixed It)
Most AI memory systems treat each piece of information as an isolated fact. Narrative Reconstruction understands how your knowledge evolves over time.