AI Coding Agents

Cloud cost awareness for AI coding agents and IDEs, with real-time pricing for IaC changes, cost tradeoff suggestions, tagging fixes, and policy-aware guardrails.

Local guardrails for AI coding agents that intercept destructive actions before they execute, now extended to Git hooks for commit and push enforcement.

Athena is a local desktop control room for AI coding agents. It combines embedded terminals, session history, shared project context, recall handoffs, and MCP-based control for tools like Codex, OpenCode, Claude Code, and Hermes.

Local-first code intelligence MCP for AI coding agents. It gives tools like Claude, Cursor, Codex, and other MCP-compatible agents an indexed evidence layer for repo search, symbol lookup, impact analysis, and test selection before editing code.

A local MCP server that builds a deterministic architecture graph of a codebase so AI coding agents can inspect modules, symbols, routes, dependencies, and cross-repo relationships from source-backed facts.

A plugin for recording AI coding agent activity in a tamper-evident local audit trail. It stores sessions, tool calls, prompts, and integrity checkpoints in SQLite and exposes CLI and UI views for status, reports, anomalies, spend, inventory, exports, and proof verification.

Offline duplicate-code detector for codebases where AI agents write most of the code. It scans for structurally duplicated functions, tracks duplication over git history, and can fail CI when new code repeats existing logic.

A field study on AI coding agents showing that a large share of token spend comes from re-reading files, with data from 47 sessions and discussion of memory-layer fixes.

A structured guide to 925 developer tools for AI coding agents, with use-when/avoid-when logic, alternatives, constraints, and health metrics.

An open-source enforcement layer for AI coding agents that adds frozen specs, tamper-detected tests, independent verification, and hard-blocking gates so unverified work cannot pass.

Mouse is a precision file-editing tool for AI coding agents. It adds coordinate-based editing, staged changes with atomic rollback, and richer tool responses to help agents make safer file edits.

An agent skill for starting or extending Django projects, with ready-made scaffolding, stack choices, and safeguards for common production pieces like auth, jobs, Redis, email, and deploy setup.

StackNudge is an open-source notification tool for AI coding agents. It adds banners and sounds when supported agents finish a task or pause for approval, with macOS support for a native panel and click-to-focus behavior.

A MotherDuck blog interview with Wes McKinney on practical AI coding workflows, including spec-driven development, continuous AI code review, and how to keep agent-generated code maintainable.

A detailed write-up about using AI coding agents to build and tune a Rust multi-Paxos consensus engine, with concrete notes on contracts, spec-driven development, testing, and performance work.