Repository Index

Self-hosted, sharable kanban for humans and agents. One 4.5 MB binary, 4.5 MB of RAM, 10 to 60 tokens per agent reply, starts in 2 ms, zero setup.

• ai-agents
• claude-code
• cli
• codex

TranslatedLocal-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health

• ai-agents
• tui
• claude-code
• codex-cli

Web app that can hash/hmac, encrypt/decrypt, and sign/verify the data, debug JWT tokens, parse and edit ASN1 structures, compute diffs, and more

• crypto
• utilities
• utility
• wasm

Spends CPU cycles so you don't spend tokens. The LLM gets a briefing packet instead of a flashlight in a dark room.