Incremental engine for long horizon agents 🌟 Star if you like it!
-
Updated
Jun 26, 2026 - Rust
Incremental engine for long horizon agents 🌟 Star if you like it!
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.
Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.
Smart(er) code reading for humans and AI agents. Reduces cost per correct answer by ~40% on average. Install: cargo install tilth -or- npx tilth
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.
CTX - Context Runtime Engine for Coding Agents
In the midst of all the tools out there that you can possibly use to keep track of them. Here's a "shovel" that just works to try them all out.
multi-depth architecture views for code understanding and generation in extremely fast speed
Fast local-first Rust CLI for codebase metrics, AST-compressed LLM context bundles, and built-in MCP server.
Monitor Claude Code sessions, costs, config, hooks, agents & MCP servers from a single Rust binary — TUI (9 tabs) + Web interface with live process tracking, budget alerts, and 30-day forecasting
Universal memory runtime for AI agents
Knowing by reasoning, not vectors. ⭐ Star this repo if you find it useful.
HOANGSA is a context engineering system for Claude Code. It solves a fundamental problem: Claude's output quality degrades as the context window fills up.
Exploring agent "thinking" animation.
A semantic engineering framework for building verifiable and traceable software.
Privacy-first recursive context gateway for AI coding agents
Sync is the project management and quality control layer your AI agents work against.
dynamic context for agent knowledge
Local-first CLI to read, compare, and hand off sessions across Claude Code, Codex, Gemini, and Cursor agents. Checkpoints, cross-agent messaging, zero npm deps.
Spec-driven development (SDD) for agents, all in a docker-like interface with your own custom workflows.
Add a description, image, and links to the context-engineering topic page so that developers can more easily learn about it.
To associate your repository with the context-engineering topic, visit your repo's landing page and select "manage topics."