The request asks what to use for memory research, which is ambiguous: it could mean research tools that keep notes and memory, or AI memory infrastructure for agents. Among the candidates, Memxus, LanOnasis, TraqrOS, Goodmem and OMEGA all offer persistent, searchable memory for AI agents, while ResearchZosho is a deep research assistant with citations and memory. Which one fits depends on whether you mean researching a topic yourself or building memory for AI agents.
A question back: Do you mean a tool to research a topic yourself (with sources and citations), or a memory layer to give your AI agents persistent memory of your research?
- 1
ResearchZoshoresearchzosho.orgwebsite read, tools not yet checked
An open-source deep research assistant that runs locally, returns a report with citations checked against sources, and keeps what it found.
- 2
Memxusmemxus.comverified and signed
An AI context engine that builds persistent context from GitHub repos and Notion docs and exposes recall and list_memories actions to search stored memory by collection.
official:MCP server · com.memxus/memxus+2 community tools built for it
for agents: memory_stats · recall · list_memories
- 3
LanOnasis Documentationlanonasis.comfound in code, not yet checked
A developer platform offering a memory service with semantic search, an MCP server, and a CLI and SDK for storing and retrieving durable memory for applications and agents.
+1 community tools built for it
for agents: memory_search · memory_list · search_memories
- 4
OMEGA: Sovereign Context Engineomegamax.coverified and signed
A local, Apache-2.0 context engine that keeps decisions, docs and agent history on your machine and provides semantic retrieval and relationship traversal over stored memories.
for agents: omega_similar · omega_timeline · omega_traverse
- 5
Goodmemgoodmem.aiverified and signed
A memory layer for agentic AI that stores documents as memories and retrieves them by similarity across spaces.
for agents: get_memory · create_memory · retrieve_memories
Sources
- 1Memxus — The AI Context Engine for Developersmemxus.com · read 2026-10-29
- 2ResearchZosho: deep research with citations and memoryresearchzosho.org · read 2026-10-29
- 3Developer Platform | LanOnasis Documentationdocs.lanonasis.com · read 2026-10-29
- 6Goodmem - Agentic AI Memory Infrastructuregoodmem.ai · read 2026-10-29
- 10OMEGA: Sovereign Context Engine | Save Tokens Locallyomegamax.co · read 2026-10-29
For agents: the 10 actions behind this answer
memory_stats · memxus verified and signed
Show statistics about stored memories (by type and collection).
· Researchzosho website read, tools not yet checked
Open-source deep research assistant that runs locally. Ask a question and get a report with its citations checked against the sources. It keeps what it found.
memory_search · Lanonasis MCP Server found in code, not yet checked
Search memories using semantic vector search
memory_search · traqr-memory-mcp verified and signed
Search memories by meaning. Returns summaries (~30 tokens each). Use memory_read to expand a specific result.
memory_search · smart-memory-mcp found in code, not yet checked
Search memories using semantic similarity with optional hybrid mode.
get_memory · GoodMem (Activepieces) verified and signed
Get Memory — Fetch a specific memory record by its ID, including metadata, processing status, and optionally the original content.
· Agentmemory for AI Coding Agents website read, tools not yet checked
Give Claude Code, Codex, Cursor, OpenAI agents, and MCP workflows governed long-term memory for repos, decisions, procedures, and team handoffs.
· Valgrind Home website read, tools not yet checked
Official Home Page for valgrind, a suite of tools for debugging and profiling. Automatically detect memory management and threading bugs, and perform detailed profiling. The current stable version is valgrind-3.28.0.
· ZenSation Research website read, tools not yet checked
Independent research lab for cognitive architectures, AI safety in public spaces, and applied AI. Open access and an open-source memory core (Apache 2.0).
omega_similar · Omega verified and signed
Find memories similar to a given memory. Use for discovering related context.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.