continuous-claude
A setup that improves context management for Claude Code using hooks, ledgers and handoffs to keep state between sessions, plus agents that run in isolated context windows.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: MIT
Overview
Continuous Claude is a development setup built on Claude Code that keeps context across sessions. Claude Code compacts the conversation when context fills up, which can lose decisions made earlier. This project uses hooks, ledgers and handoffs to hold state between sessions, and runs specialized agents in isolated context windows. It also adds MCP execution without context pollution, a memory system and token-saving code analysis.
Key features
- Hooks keep state through ledgers and handoffs
- Agents orchestrated in isolated context windows
- MCP execution that avoids polluting context
- Memory system and TLDR code analysis to save tokens
Best for
Heavy Claude Code users who lose track of decisions when context is compacted and want a persistent, multi-agent workflow. It is a large setup, so expect some configuration effort.
- Upstream
- parcadei/Continuous-Claude-v3
- Fork on GitHub
- Guo-astro/continuous-claude
- Upstream stars
- 3.9k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- MIT
- Forked
- 2025-12-25
- Sync status
- In syncLast synced 2026-11-08
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub