Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
The repo map your coding agent is forced to use — ~98% fewer tokens (up to 99.9% per task) to understand a TS/JS codebase. PageRank hubs, Aider-style symbol ranking, token-budgeted digest, --any router, wired into the agent loop.
Navigate your way - manual steering, steered autonomy, or autonomously. Kompass keeps AI coding agents on course with token-efficient, composable workflows.
The token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.
Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server; works with 15+ agents.
Agent Native Format (ANF): a token-minimal view format that translates live system state into far fewer tokens for AI agents. Ships a Go encoder, a Kubernetes translator, and a governed execution runtime. v0.1 PoC.