PAGI research
We study agent memory, learning from experience and authorized work between conversations. PAGI is the research goal; the work is still in development.
01Research lab & project incubation
Open sourcePAGI research.
We research local agentic systems and incubate AI projects. Our ongoing work toward Pseudo-AGI studies how agents can retain knowledge, continue tasks between sessions and learn from experience.
PacoMind and our PAGI research are open source. We support the pursuit of open access to AGI.
Request illustration
PacoMind architecture
PacoMind retains memory between requests while Hermes runs conversations and tools.
PacoMind / illustrative request
Memory across conversations
A request reaches Hermes
A message arrives through a configured conversation channel.
Inspect the architecture
Aevonix ResearchSystems & services
01 / Research lab
PacoMind architecture
Ongoing, open source research toward PAGI (pseudo-AGI).
Messages and user direction
Messages arrive through Hermes channels. A person can provide context, correct the agent’s understanding and steer work across conversations.
Conversations → Hermes runtimeHermes runs the agent
Hermes handles conversations, model requests, tools, workers and schedules. PacoMind connects through plugins, a memory provider and request hooks.
Hermes ↔ PacoMind · Hermes → models and toolsTool and worker execution
Hermes executes tools, workers and scheduled tasks. PacoMind keeps shared work state available across conversations, so users can inspect or redirect it within the deployment’s permissions.
Hermes → tools, workers and schedulesPersistent memory and work state
PacoMind retains original evidence and attributable corrections, recalls relevant context, and keeps identity and shared work across sessions. The deployment stores these records independently of the selected model.
Hermes ↔ memory and work context · PacoMind → selected modelsLocal and replaceable models
Hermes and PacoMind each use their configured models. Local inference supports normal operation without a cloud model; changing a model does not replace the agent’s stored memory or identity.
Hermes + PacoMind → model inferenceIn development and validation. Read the architecture
PacoMind architectureSelect a module for details
Selected module
Messages and user direction
Messages arrive through Hermes channels. A person can provide context, correct the agent’s understanding and steer work across conversations.
Conversations → Hermes runtimeHermes runs the agent
Hermes handles conversations, model requests, tools, workers and schedules. PacoMind connects through plugins, a memory provider and request hooks.
Hermes ↔ PacoMind · Hermes → models and toolsTool and worker execution
Hermes executes tools, workers and scheduled tasks. PacoMind keeps shared work state available across conversations, so users can inspect or redirect it within the deployment’s permissions.
Hermes → tools, workers and schedulesPersistent memory and work state
PacoMind retains original evidence and attributable corrections, recalls relevant context, and keeps identity and shared work across sessions. The deployment stores these records independently of the selected model.
Hermes ↔ memory and work context · PacoMind → selected modelsLocal and replaceable models
Hermes and PacoMind each use their configured models. Local inference supports normal operation without a cloud model; changing a model does not replace the agent’s stored memory or identity.
Hermes + PacoMind → model inferenceIn development and validation. Read the architecture
Research
Research and incubation
Our lab develops PacoMind and supports other AI projects through incubation.
Local agentic systems
PacoMind connects to Hermes and stores agent memory, identity and shared work independently of the models it uses. It supports local inference.
AI project incubation
We incubate AI projects alongside our own research. PacoMind is our featured public project. For incubation inquiries, email Maggie@aevonix.com.
Open access to AGI
We publish PacoMind’s code and research notes so others can inspect, use and contribute to the work. This supports our mission of pursuing open access to AGI.
Contact