Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
-
Updated
Nov 16, 2026 - Python
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sessions and follow progress in the Mac app.
Pre-compaction hooks + a CAS-guarded task pointer that keep Codex agents on-goal across context auto-compaction — no mainline drift, no duplicate work, no conflicting progress in long runs.
Zero-touch session rotation and supervision for Claude Code
Secure AI Memory MCP Server with Multi-Tenancy, Dynamic Project Routing, Auto Session Briefing, Personal+Team Summaries, Hybrid Search, Knowledge Graphs, GitHub (Issues, PRs, Actions, Kanban, Milestones), Git Mining, Team Collaboration, Native CLI, Analytics, Markdown I/O, Audit Logs, OAuth 2.1, HTTP/SSE/stdio & Unified Code Mode.
Local-first operating memory for AI coding agents - Claude Code, Codex, and any MCP client. Tracks decisions and their evolution. SQLite + on-device embeddings, no cloud.
One memory, every terminal — a shared memory layer for any MCP client.
Repo-local checkpoint and resume skills for coding agents. Handoffs are plain markdown under .agents/checkpoints/, so Codex can write one and Claude Code or opencode can pick it up later — across sessions, machines, and model switches.
A shared plan, check-offs and resumable task progress for every coding agent in a project
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
Cross-session context persistence for AI coding assistants
Small, sharp, agent-agnostic skills that keep an AI agent's work honest.
Session continuity for AI coding agents — your agent picks up where it left off. Persistent memory for Claude Code, OpenAI Codex CLI & Google Gemini CLI, sharing one local db: auto context injection, compaction handover, semantic search (KO/EN/JA), error→solution recall. 100% local, zero config, zero API cost.
A local handoff gate and human-confirmed, verified /new controller for managed Kimi Code sessions.
Session continuity for Claude Code and Codex: one append-only log per repo, read back at session start and after compaction.
Project governance for AI-assisted development. Structured planning, sprint workflows, decision tracking, and scope enforcement — built as plain markdown files and slash commands on top of Claude Code.
A working reference for running AI agents with Kanban discipline. Operating model, knowledge system, persona files, and board CLI extracted from a production multi-agent delivery system.
Worktrail — a durable, byte-exact record of engineering work for AI coding agents (MCP server + screen). Source-available.
Cross-LLM context handoff — creates handover.md so Claude, Codex, Gemini, or any LLM can continue your work without mistakes when context runs out
To associate your repository with the session-continuity topic, visit your repo's landing page and select "manage topics."