Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.
Declarative PostgreSQL schema management that turns SQL files into replay-safe migrations, generated TypeScript types, Zod validators, and guarded sync. No Docker, no shadow database, no ORM schema layer.
Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds compact context packs for Claude Code, Codex, Cursor, MCP, and more.
Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.
Deterministic Stop-gate and code-graph context for AI coding agents: blocks only net-new findings and gives the loop a structural map of the codebase, locally, with no model in the gate.
Run Claude Code, Codex, Copilot, Gemini, OpenCode and Amp side by side in isolated Git worktrees, with shared issue ownership, reservations and explicit handoffs.
Cross-harness AI skill portability CLI. Author an agent skill once, sync it into Claude Code, Cursor, Copilot, Codex, OpenCode & 45+ AI coding agents. Safety scanner, content-hash drift detection. A package manager / dotfiles for AI coding agent skills.
Backthread keeps the thread on what your AI coding agent ships — it captures the why behind every change and turns it into a living 'How it works' view of your codebase you can actually query.
Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.
repomap: token-budgeted repo map for AI coding agents. Walks any repo, ranks files by import refs, emits orientation in under 4000 tokens. Stdlib-only Go, zero deps, tree/JSON/HTML. go install github.com/AkashPriyadarshii/repomap/cmd/repomap@latest