Claudebin: Export and Share Your Claude Code Sessions
Claudebin is a plugin designed for users of Claude Code, allowing the export of sessions into URLs, which include entire message threads, file modifications, bash commands, and web/MCP calls. The tool aims to facilitate sharing and resumption of coding sessions across different environments.
The plugin captures all aspects of a session within Claude Code, which is especially useful for lengthy development processes. This includes:
- The full message thread for context and continuity.
- All file reads and writes to track changes and document the development process.
- Bash commands executed during the session to document command-line interactions.
- Web and MCP calls for integrations that occurred.
With Claudebin, you can distribute a URL via emails or chat, attach it within a pull request, or even embed a snippet in documentation. This makes it straightforward to collaborate on the same work across different devices or share progress within a development team.
The project is open-source and accessible on GitHub for further exploration or contribution.
📖 Read the full source: HN AI Agents
👀 See Also
read-once: A Claude Code Hook That Prevents Redundant File Reads
A developer built a PreToolUse hook called read-once that tracks files Claude Code has already read in a session, blocking re-reads of unchanged files and using diffs for changed files. The tool saves thousands of tokens per session by preventing Claude from repeatedly reading the same file content.
Local Memory System for AI Coding Tools Extracts 2,600+ Facts from Conversation Logs
A developer built a local memory layer that ingests conversation logs from Claude Code, Factory.ai, and Codex CLI, extracts structured facts using a local LLM, and auto-injects context into new sessions. After months of use, it has indexed 13,000+ messages and extracted 2,600+ facts.
Developer Achieves Sub-Second STT/TTS Latency with Local Whisper and Coqui-TTS Servers
A developer has open-sourced local server implementations for Whisper STT and Coqui TTS that achieve ~0.2s speech-to-text and ~250ms text-to-speech latency, enabling conversational AI agents without cloud dependencies.
Omnicoder-9B Performance Review: Speed vs. Tool Calling Issues
Omnicoder-9B, a coding-focused model fine-tuned on Qwen3.5 9B with outputs from Opus 4.6, GPT 5.4, GPT 5.3 Codex and Gemini 3.1 Pro, shows strong performance on mid-tier hardware but has tool calling issues in IDEs.