vibehacker
News
GitHub (goyohan0611-png/graph-mind) ·

Graph-MIND gives Claude Code, Codex, Cursor and other agents one shared local memory, no LLM calls to save

Shown on HN Oct 26, the AGPL-3.0 beta stores every conversation turn verbatim on your own PC with secrets masked, then hands any MCP-connected agent a ~3k-token packet of the turns that answer a question about the past; the author reports 88.8% on LongMemEval. Install with pip install graph-mind-memory && graph-mind-install, or claude mcp add graph-mind-memory -- python -m graph_mind.mcp_server for tools only; it's used daily on Windows, while macOS and Linux only pass CI so far.

More news

View all

GPT-6.1 Terra is now GA in GitHub Copilot, a cheaper OpenAI model for everyday agentic coding

As of Oct 26, OpenAI's newest model is rolling out to Copilot Pro, Pro+, Max, Business and Enterprise in the model picker across VS Code, Copilot CLI, the cloud agent, JetBrains, Xcode and more, pitched for terminal and well scoped coding tasks at a lower cost than GPT 6.1 Sol. GitHub says it beat GPT 5.6 Terra on terminal and C tasks in early testing, and it's billed at provider list pricing under usage based billing…

GitHub Changelog

Cline 4.1.26 adds a Local/Cloud model toggle for cloud tasks and quietly changes provider defaults

Released Oct 26, the extension lets you pick a separate model for cloud tasks under Settings API Configuration, shows a progress card while a cloud sandbox clones your repo, and makes GPT 6 models work on OpenAI and Azure compatible endpoints. With no model chosen, the Cline provider goes back to Claude Sonnet 5.5, and most other providers now default to Kimi K3.1 Pro, MiniMax M3.1 Flash or DeepSeek V4.1 Flash, so pin your model if you don't want a surprise switch…

Cline SDK 0.2.0 stops runaway re-compaction and drops Gemini native search that broke free keys

Released Oct 26, a compaction size estimate that ran about 7x too high (triggering compaction every few tool calls) is fixed, and the gemini provider no longer sends native Google Search, which made Gemini 3+ free tier keys fail every turn with 429s. Starting a session mid run now reattaches to the live run instead of orphaning it, model retries drop from 5 to 3, and ClinePass now defaults to Kimi K3.1 Pro…

Kolo lets your team join one local Claude Code, Codex or opencode session from a browser link

Shown on HN Oct 26, the AGPL 3.0 Go binary starts a hub and agent host with kolo up and prints an invite link, so teammates can watch, type prompts, approve steps or take over the same terminal without installing anything, while the host keeps read only seats for observers. It's an experimental alpha where agents run with the host's permissions, so the README says to start in a dedicated VM (Show HN)…

Spotted something we missed? Start a thread.