madewithlaya

Catalog / Documents & data

0079GitHub

Chat Seek: search past Claude Code, Codex and OpenCode chats in VS Code, reranked by Laya

Describe a past conversation in plain language and Chat Seek finds it across local agent histories, reranks with the receptron Laya runtime, and offers a Resume action.

Open source ↗ github.comcostfree, localtime-
fstandhartinger/chat-seek-vscodeREADME ↗
**Point your coding agent at this repository and ask it to install Chat Seek in your local VS Code—see [Agent installation instructions](#agent-installation-instructions) below.**

# Chat Seek

Find past **Claude Code, Codex, and OpenCode** conversations from a plain language description, inside VS Code.



[Demo video](media/demo.mp4) · [Narrated explainer](media/explainer.mp4). These videos show the original UI with illustrative excerpts; the current version also has dates, summaries, and resume actions.

Chat Seek searches local user and assistant messages, then uses the [Laya local decision model](https://github.com/receptron/laya) to rerank likely matches. Optional one-sentence AI descriptions help you recognize a chat. Cards show its last activity (“1 week ago”), with the exact date on hover, a readable excerpt, and a **Resume in Claude Code / Codex / OpenCode** action.

## Open and pin Chat Seek

Press **Ctrl+Shift+P** (**Cmd+Shift+P** on macOS), run **Chat Seek: Search past AI chats**, and type in the search box. You can also click the **Chat Seek magnifying-glass icon in the Activity Bar** to use the sidebar.

Click **Pin search tab** to keep the editor tab handy. You can right-click the Activity Bar to show Chat Seek if its icon is hidden, or drag its view to your preferred sidebar. If commands do not appear immediately after installation, run **Developer: Reload Window**.

**Resume** opens the matching CLI in a VS Code integrated terminal using its session ID and original working directory when available. It does not automatically submit a new prompt. The CLI must be installed and signed in within the same environment as the extension. This launches the CLI, not a vendor's proprietary chat sidebar. An archived or moved session may no longer be resumable by it

Also filed under Documents & data

  1. 0104

    zero-shot-ie-bench: GLiNER 2.5, GLiFormer, GLiClass, Laya, Von and Jev in one web UI

    Seven zero-shot extraction and classification families demoed, benchmarked and cross-compared, with sizes, licences and costs in one table.

    @umstek · Documents & data · free for the local rows

  2. 0103

    Zero-shot benchmark: Laya's advertised win over Jev does not reproduce on four datasets

    Frozen protocol, raw predictions, calibration and latency for Jev 1.13, PrismNLI-0.4B and Laya. Laya ties Jev on dair-ai/emotion and trails by 10–33 points elsewhere.

    @elcronos · Documents & data

  3. 0102

    jevbench: Jev vs GPT-5-mini, Claude Sonnet 5, fine-tuned DistilBERT, BART NLI and Laya

    Six classifiers over SST-2, AG News and more, reporting accuracy, macro-F1, ECE, p50/p95 latency, throughput and cost side by side. Laya runs locally on MPS or CPU.

    @dhruvmehra · Documents & data · $0 for the local rows

  4. 0098

    Agentic GraphRAG over S&P 10-Ks with Laya as a shadow decision engine beside Jev

    Anthony Alcaraz's talk demo routes typed decisions through Jev and shows Laya's answers beside them. On the TSMC run Laya rejected every true claim; that's the point.

    @AnthonyAlcaraz · Documents & data · free (Laya shadow); Bedrock for reasoning