daseinlabs/parsec

Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

A tiny single-file coding agent for self-hosted models (llama.cpp / vLLM / SGLang).

The Open Runtime for AI Agents

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

Build agent that uses 80% less token and delivers better results.

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.