pureBOT
The part that does the work.
pureBOT takes a task, chooses the seat and the model to run it, calls the tools it needs, checks the output, and asks for approval only where the operator has reserved a decision. It runs PureTensor's own operations today. Below is its engineering record, including how it was built out of a personal AI agent from 2024, so you can judge the claim rather than take it on trust.
The agent that outgrew itself
2024 · First commit. A reaction to bloated agent frameworks.
The monolith began as a reaction. The first wave of open-source agent frameworks had proven the pattern (markdown identity files, tool use, multi-channel ingress) but brought mass dependency, untested security boundaries, and an abstraction tax that made debugging impossible.
Ours stripped the idea to its essentials: a minimal agentic harness around Claude, with a three-tier memory system, a multi-engine inference router, and a policy-driven security framework. The goal was a personal AI agent you could actually trust on production infrastructure.
From agent to nervous system
2025–2026 · The chatbot stopped being the point.
The inflection point came when the monolith’s operational modules started doing more useful work than the chatbot interface they were built to serve.
One by one, the modules were absorbed into the infrastructure. The chatbot was the last thing standing, and it was the least useful part.
The nervous system
Naming the operational reality that was already there.
pureBOT is what remains after the agent identity is removed and the operational reality is named. It coordinates autonomous infrastructure modules across PureTensor’s compute fleet.
The biology analogy is deliberate. pureBOT is the autonomic nervous system of the cluster. It does not think. It coordinates.
Long-running monitors watch external signals so the operator does not have to. Each one is a self-contained module with its own gating and cadence.
Tools are registered through the Model Context Protocol so the same surface can be reached by any LLM that speaks MCP.
A systemd-driven heartbeat fires routine work (gather, reason, act, notify) without a chatbot in the loop.
A nightly Mem0/MemGPT-inspired pipeline distils session traces into durable knowledge and prunes what no longer applies.
How the pieces fit
Channels feed observers. Observers and the dispatcher feed the core. The core routes to one of three inference tiers, draws on tools and memory, and emits events back through the heartbeat.
Lineage
What carried over, what got renamed, what got cut.
Most of the monolith is still running. It just stopped pretending to be one thing and started being many. The table below is the continuity map: who became who.
A project that changed shape, not a product launch.
The research behind pureBOT
- Sep 26, 2026Click Accuracy Picks the Wrong Browser Agent: Choosing a Self-Hosted Computer-Use Model on 39 Live Tasks
- Sep 30, 2026The Multiplexer That Knows Its Agents: Herdr Against tmux for Concurrent Coding Agents, and Compiling Out the Phone-Home
- Sep 29, 2026Hybrid Mamba Cannot Cache a Transcript: Choosing a Seat for a Live Co-Pilot by Time to First Answer
- Sep 25, 2026Spend Is Width Times Turns: Where an Orchestrating Agent's Tokens Go, and What a Diet Moved
- Sep 1, 2026Green Gate, Lost Hunks: Nine Ways an Automated Merge Train Dropped Merged Code While Every Test Passed
- Aug 30, 2026The Reliability Champion Is Not the Single-Shot Champion: pass^5 Inverts a Leaderboard
Built, running, and yours.
pureBOT is the part of pureWRIGHT that does the work, alongside pureMIND, which remembers everything, and pureMEND, which repairs what breaks. It runs PureTensor's own operations today and is deployed for enterprise inside your boundary. There is no pricing page; an engagement begins with a conversation with the engineers who run it.