Newest first · filterable notes
Notes from the coding terminal.
Product launches, feature notes, and engineering decisions behind a local-first AI coding runtime.
7 posts · newest first
All posts
MendCode is the anti-chatbot harness for the loop era
Welcome to MendCode: a local-first AI coding harness built around agents, loops, permissions, memory, packages, review, Usage Insights, and a terminal surface developers can actually own.
Context intelligence is the real AI coding interface
Prompt context is not a personality switch. MendCode uses context options, repo instructions, model roles, packages, and custom AGENTS.md-style guidance to decide what belongs in the model window.
Own your cockpit: the coding terminal is product surface now
Themes are not enough. Agentic work needs profiles, widgets, custom pages, package-shaped workflows, and a terminal surface that matches how the team actually thinks.
Memory without lore: agents need reviewable continuity
Agent memory is useful only when the user can inspect, scope, approve, reject, and clean it up. Otherwise it becomes invisible lore that bends every future session.
Founder economics need local insight, not creepy analytics
AI agents make small teams capable of directing far more work. Usage Insights should help them operate that machine locally without turning developer behavior into surveillance.
Packages are how teams stop copy-pasting their operating system
The good prompt is not enough. MendCode packages make workflows composable: skills, profiles, prompts, widgets, pages, context, themes, MCP, and policy in one inspectable unit.
Permission theater sucks. Agent speed needs real boundaries.
As agents get faster, permission prompts cannot be vague interruptions. They need blast-radius context, smart review, and visible boundaries inside the coding surface.