token-optimization

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

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

lowfat - slim your command output. strips noise, saves tokens.

Headroom for macOS — cut Claude Code and Codex token costs by ~50%

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.

LLM-ready reasoning surface over logs

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacement for grep/cat/read/ls in Claude Code, Codex, Cursor, Aider, OpenHands.

Config-driven CLI tool that compresses command output before it reaches an LLM context

CTX - Context Runtime Engine for Coding Agents

A high-performance, ergonomic web framework for Rust with native AI/LLM support.

Zed extension for Headroom — context compression for AI agents

You put an agent into an Elpis, and it becomes Elpis; Be Elpis my friend.

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Context Limiter & Output Vetter for context bloat. It is a highly specialized, structure-aware JSON built specifically to intercept and compress MCP responses before they annihilate your LLM's context window.

The most intelligent context optimization engine for coding agents. Code-aware AST parsing across 17 languages. Command rewriting. Test, build, and git output compression. Token budget cascading. Built in Rust.

8v is one binary that reads, writes, searches, checks, builds, tests, and formats code, using fewer input and output tokens than the agent's native tools.

Local, provider-neutral compression for LLM prompts, tool schemas, JSON, logs, and diffs. Lossless, receipt-audited, no ML tax.