[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD, typed IDs, markdown knowledge graph, Claude Code skills & hooks.

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

A memory layer for AI Agents

Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix commands. Zero API calls

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

Universal memory runtime for AI agents

Persistent memory for AI coding agents

A Git-native knowledge layer for your team — and a set of tool suite that keeps it alive.

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

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.

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.

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

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

C.O.N.T.EX.T is designed to compress complex, multi-domain conversations into machine-optimized "Carry-Packets." These packets achieve a crystallization point of 0.15 entity/token, ensuring that a receiving model can reconstruct the original context with near-perfect fidelity.

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

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

A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!

Stop "vibe coding" and start Stream Coding, the 10-20x velocity methodology for AI-accelerated development. Includes the official SKILL.md for Claude/Cursor/Windsurf and the complete Manifesto.

Project memory for coding agents and humans: the reasoning behind a codebase as Markdown in the repo, versioned by Git, so nothing rejected is proposed twice. No database, no daemon, no account.

Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.

Structured planning and persistent context for AI coding agents. Plan multi-phase work once and any agent (Claude Code, Codex, OpenCode) executes it across sessions without losing the thread.

AI builder operating system. Turn Claude Code from a per-session tool into a workspace that remembers, maintains itself, and never goes stale. BASE = Builder's Automated State Engine.

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.