Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.

A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.

Structured planning and persistent context for AI coding agents. Plan multi-phase work once and any agent (Claude Code, Codex, OpenCode) executes it across sessions without losing the thread.

Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.

Visual planning and context control for shipping big apps with AI coding. Build from scratch or map existing repos. Dossier maps user workflows, sets agent context per feature, builds, tests and ships from one interface.

AI builder operating system. Turn Claude Code from a per-session tool into a workspace that remembers, maintains itself, and never goes stale. BASE = Builder's Automated State Engine.

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

Stop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.