Tollecode just got Memory.
Agents can now remember your workspace context like a persistent brain for your project — making long-running engineering tasks, multi-step workflows, and delegated agent work far more consistent.
Tollecode is a local-first AI coding assistant built for real engineering work:
File reads
Shell commands
Sub-agents
Full control over execution
New Memory Commands:
/memory — Show memory status & commands
/memory on|off — Enable or disable workspace memory
/memory list — List all memory entries
/memory view — View full content of entry #n
/memory search — Keyword search across memory
/memory query "" — Ask the LLM questions about memory
/memory summarize — Generate thematic summaries
/memory delete — Delete memory entries
/memory stats — View memory statistics
The goal is simple:
Give AI agents continuity and workspace awareness without sacrificing local control.
Still experimental. Still evolving. But already making agentic coding workflows feel much smarter.
Replies
I’ve been waiting for something like this . Persistent memory inside a local-first coding assistant makes long engineering sessions feel way less repetitive and fragmented.
@nitesh_kumar98 I’m really into the local-first approach here. Having AI remember my workspace without sending everything to the cloud feels like the right balance.
@nitesh_kumar98 @malani_willa For me, /memory query sounds like the killer feature. Being able to ask the assistant about previous decisions or project structure could save serioius time
Tollecode
@nitesh_kumar98 @malani_willa @simran_kumar
Yeah, that’s exactly the workflow shift I was aiming for.
I am glad you like it
@nitesh_kumar98 @simran_kumar @bernard_ossei_agyei thnks!
Tollecode
@nitesh_kumar98 @malani_willa
That balance was one of the main reasons I built it this way.
A lot of coding tools are becoming increasingly cloud-dependent, but for real engineering workflows, keeping workspace context local matters, both for privacy and for control.
The idea is to give agents long-term memory and continuity without taking ownership of your codebase or workflow away from you.
Tollecode
@nitesh_kumar98 I am glad you like this feature.
Most agent workflows lose context too quickly, so you end up repeating the same instructions, architecture decisions, and project details over and over again.
Memory gives agents persistent workspace awareness across sessions, and you can query it directly without wasting tokens re-explaining context every time — all while keeping everything local-first and under your control.