Context Engineering: Build Consistent, Accurate, Predictable AI Systems

[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.

A context engine that treats skills as software.

Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

Privacy Code Scanner and Dataflow Context Engine for AI coding agents

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

deep, reliable and confidential coding-context

A memory layer for AI Agents

CTX - Context Runtime Engine for Coding Agents

The open-source company brain. Run your entire company with AI agents, skills, and a self-improving context.

The theory of LLM wikis, running as one. A framework for agent-operated knowledge: typed, linked, review-gated markdown your agents execute.

Universal memory runtime for AI agents

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

Stop re-explaining your data to your AI every session. The individual-analyst context layer, delivered over MCP (Claude Code / Cursor / Codex).

Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.

📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev

Agentic AI explained with chickens 🐔 every pattern a runnable, CI-checked file.

AI Badger - Local-first tool that extracts focused repo context for any AI chat (Claude, ChatGPT, Grok, etc.) without wasting tokens on irrelevant files.

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, then reversibly disables the dead weight. No proxy, no compression.

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.