Self-Compacting & Bi-Temporal Agent Memory: The Next Evolution of Context Engineering
In Closing the Cognitive Loop: Automated Context Pre-Injection, Self-Expanding Eval Gates, and Zero-Touch Knowledge Federation, we wired our local AI agent cognitive stack—spanning out-of-band NREM/REM memory dreaming, self-curating Obsidian semantic stores, and federated Teacher–Student knowledge transfer—into a single autonomous pipeline. Once that loop ran continuously across multiple engineering sessions and federated curriculum bundles, a new… Read More: Self-Compacting & Bi-Temporal Agent Memory: The Next Evolution of Context… »
Closing the Cognitive Loop: Automated Context Pre-Injection, Self-Expanding Eval Gates, and Zero-Touch Knowledge Federation
Equipping Local AI Agents with Official Obsidian Skills: From Bases and Headless Sync to Defuddle and Knap Pipelines
Zero-Trust Signal Gateways for Local AI Agents: Hardening JSON-RPC Envelopes, Attachment Quarantine, and Execution Boundaries
Federated AI Agent Memory: Moving Distilled Knowledge Between Teacher and Student Machines Across Engineering Teams
Over the previous installments of this series—from Giving Local AI Assistants Long-Term Memory and Learning While You Sleep: Out-of-Band Memory Dreaming to Hardening Claude Code’s Memory: Mistake Ledgers, Per-Prompt Context, and Verifying the Dreamer Itself and Hardening Local AI Agents: Procedural Skills, Mistake Ledgers, and Real-Time Verification—we solved single-machine amnesia. An AI coding assistant running… Read More: Federated AI Agent Memory: Moving Distilled Knowledge Between Teacher and… »
The Autonomous Homelab: Building a State-of-the-Art Local AI Agent Architecture
The artificial intelligence industry is currently experiencing a profound architectural divergence. On one side lies the Consumer Chat Wrapper: slick, interactive web UIs powered by multi-trillion-parameter frontier models. Yet despite their raw intelligence, they operate in a state of permanent cognitive amnesia. Every time you open a new tab or restart a session, the model… Read More: The Autonomous Homelab: Building a State-of-the-Art Local AI Agent Architecture »
Supercharging Local AI Agents on Signal: Fast-Paths, Live Typing Indicators, and Session Continuity
Running a full-scale agentic AI—like Google Antigravity (agy), Claude Code, or a local LLM with tool-use capabilities—directly inside your homelab or developer workstation gives you immense power. You can orchestrate deployments, query infrastructure metrics, check smart home sensors, and run automated diagnostics without exposing any private data or API keys to third-party consumer chat wrappers.… Read More: Supercharging Local AI Agents on Signal: Fast-Paths, Live Typing Indicators,… »
Hardening Claude Code’s Memory: Mistake Ledgers, Per-Prompt Context, and Verifying the Dreamer Itself
This is the sixth post in my series on giving Claude Code a long-term memory in Obsidian. The earlier posts covered session archiving and context injection, sub-second vault search, self-curating memory, out-of-band “dreaming” and teaching the agent real Obsidian syntax. In Hardening Local AI Agents: Procedural Skills, Mistake Ledgers, and Real-Time Verification I described a… Read More: Hardening Claude Code’s Memory: Mistake Ledgers, Per-Prompt Context, and Verifying… »
Hardening Local AI Agents: Procedural Skills, Mistake Ledgers, and Real-Time Verification
In Learning While You Sleep: Implementing Anthropic’s Out-of-Band Memory “Dreaming” in Obsidian Part 4 of this series]], we implemented Anthropic’s out-of-band “Dreaming” architecture for my local CLI assistant, Google Antigravity (agy). By running a nightly batch consolidation cycle over raw session transcripts, the agent gained the ability to autonomously distill episodic events into durable declarative… Read More: Hardening Local AI Agents: Procedural Skills, Mistake Ledgers, and Real-Time… »