Havuz

CTX - Context Runtime Engine for Coding Agents

The context spine that 10x's every AI coding session. Live in 8 IDEs (Claude Code, Cursor, Cline, Continue, Aider, Codex, Windsurf, Zed) via

Claude Code skill — delegate coding tasks to Mistral Vibe, supervise via git diff & save 50-90% Claude token usage

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

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Measured, monotonic, lossless input savings for Codex.

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Agentic Runtime

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

token-ninja routes deterministic shell commands locally — zero LLM calls, ~19µs latency. Works silently inside AI tools via MCP.

MCP server for Unity Editor — 160 tools for scene, assets, animation, VFX, playtest & more

A tool that replaces everything that can be deterministic in repository work: search, symbols, callers, task scope, history, review and Git

Chrome Extension that lets you continue any AI conversation anywhere—without losing context. No more copy-paste—move full context across AI

Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude C

A lossless token-optimization codec for LLM agents — cut input tokens up to 82%, nothing dropped, every fact kept. Drop-in proxy + one-line

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior acro

See where your Claude Code tokens go — cost per call scales 4.3x with context size. Hooks + SQLite + dashboard + MCP server for context wind

Control plane for AI coding agents: route tasks, reduce token spend, run multi-agent workflows, fallback executors, and track cost per task.

Community skills for Claude Code: token optimization, productivity workflows, and development best practices. All skills tested with TDD met

Open WebUI filter that defers MCP and builtin tool schemas until the model asks for them by name, cutting per-call prompt tokens

Stop Claude Code from burning through your quota in 20 minutes. Auto-rotates oversized sessions and preserves context.

Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

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 ne

Pith is the hook that makes Claude Code sessions last 3x longer.

Turn Google Drive PDFs into Obsidian wiki notes via NotebookLM MCP without loading full PDFs into Claude context

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.

Zed extension for Headroom — context compression for AI agents

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

Claude Code skills for developers who code like cats — never more effort than the problem requires.

CLI output compressor for Claude Code. Reduces token consumption by 50–90% by compressing verbose command output before it enters the con

Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs. 🍜

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

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, the

Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.

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

TERSE - a hierarchical state language for humans and AI agents.

A compiler for AI coding tasks: pre-resolves repo facts (callers, git history, blast radius, bug-site source) before your coding agent's fir

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

Codex Cost Router Skills - preflight task routing skills for Codex to reduce token waste, choose model tiers, reasoning effort, permissions,

MCP server that shrinks logs, JSON, docs and web pages before your AI reads them. Offline, deterministic, ~3ms, no API key. 66% fewer tokens

Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Guardian Runtime sits securely on your machine, acting as a bodyguard for your code. Whenever you use AI tools like Cursor or Claude Code, i

Neura lets you run long, tool heavy coding sessions without blowing up token costs by compressing old context into references and only resto

Context optimization layer for LLMs. 65-90% token savings with zero quality loss. Drop-in proxy for Claude, GPT, Gemini, and local LLMs (Oll

Claude Code skill — delegate coding tasks to Opencode, supervise via git diff & save 50-90% Claude token usage

Call the Google Antigravity CLI (agy) headlessly from any non-TTY context — Windows ConPTY + POSIX pty + MCP server. Fixes the empty-output

Use any AI model, locally or in the cloud, while tracking on-device token usage and collecting token telemetry data.