vibeforge1111/keep-codex-fast

给 Codex 全局记忆定期减负的 skill：检测重复、清理过期线程、压缩冗长表达、添加自定义全局规则 / A skill that puts Codex global memory on a periodic diet: dedupe, prune, compress, add global rules

Libera espacio de tus conversaciones de IA (Claude Code, Codex, OpenCode, Antigravity, Command Code) recortando lo anterior a la última compactación — con respaldo previo. Reclaim AI conversation storage safely.

Safety-first GUI and CLI for auditing, backing up, importing, cleaning, and trimming Codex conversations without editing internal storage.

Lossless context management for Claude Code

Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

Local-first memory for AI coding agents. Indexes your repo and delivers bounded, provenance-backed context with drift checks and strict safety controls. No cloud, no API keys.

Maximize Claude's intelligence with MemTree, an advanced context-management engine

Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.