Draft:Lore.link

  • Comment: In accordance with the Wikimedia Foundation's Terms of Use, I disclose that I have been paid by my employer for my contributions to this article. Paulina.lore (talk) 00:14, 17 June 2026 (UTC)

Lore
DeveloperTanagram
Release2026; 0 years ago (2026)
Operating systemWeb, command-line interface
PlatformCross-platform
TypeDeveloper tools, AI collaboration
LicenseProprietary (freemium)
Websitelore.link

Lore is a software product developed by Tanagram that provides infrastructure for capturing, sharing, and reusing the work done in AI coding-agent sessions. The product lets a user turn a session with a coding agent — including its prompts, tool calls, and code diffs — into a durable, shareable web page, and adds collaboration, distribution, and analytics features on top of that captured data. Lore markets itself around the idea of "durable agent knowledge" and describes its aim as putting "the world's AI sessions in one place."[1]

Overview

Lore is designed to work across multiple AI coding tools rather than a single vendor's agent, with stated support for sessions from Claude Code, Codex, Cursor, and Cowork.[1] Its core mechanic is a /share command that a user runs inside a coding-agent session; the command converts that session into a URL that can be sent to teammates or made public, producing a searchable, forkable artifact with summaries, decisions, and comments under a public, private, or workspace visibility model.[1]

The product follows a product-led growth model. It offers a free tier and uses domain-based workspaces, so colleagues who sign up with the same email domain are grouped together automatically. Paid tiers include a "Creator" plan, which adds a dedicated tab for managing reusable agent "skills," and a per-seat "Team" plan, which adds workspace-wide sharing and a code-review feature.[1]

Features

Session sharing

The foundational feature of Lore is the conversion of an AI coding session into a persistent, linkable artifact. Rather than relying on copied-and-pasted screenshots or transcripts, a shared session preserves the prompts, the tool calls the agent made, and the resulting code changes, so that others can review how a result was actually produced.[1]

Lore CLI

The Lore command-line interface (CLI) is the primary mechanism by which sessions are ingested into the platform. After a user authenticates with a command such as lore login, the CLI captures sessions from supported coding agents and uploads them to a Lore workspace, where they become shareable artifacts. The /share command is exposed through this tooling, and the CLI is the path through which session data — the basis for Lore's analytics and skill-measurement features — is collected.[1]

Lore plugins

Lore is distributed for some host applications as a plugin. In Anthropic's Claude desktop application, for example, the Lore plugin is installed by adding the tanagram/lore-plugin marketplace and installing the Lore plugin from it, which makes the /share command and related functionality available inside the host's sessions.[1] The plugin model lets Lore integrate with multiple agent environments without each one needing a bespoke build.

Smart Skill Library

Lore's Smart Skill Library is a feature for distributing and maintaining reusable agent "skills" across a team. It allows a skill to be published once and kept automatically up to date for everyone who uses it, including non-technical teammates, removing the need for manual reinstallation. In addition to distribution and version control, the Smart Skill Library is positioned around measuring whether skills actually work — reporting how often each skill is invoked and whether it succeeded in resolving the request — across different coding agents. Tanagram describes this as a "closed loop" spanning publishing a skill, running it, and measuring its outcomes.[1]

Analytics

Because Lore ingests the underlying session data through its CLI, it can provide analytics on how agents and skills are being used, including which skills are invoked most often and signals about token spend and effectiveness. The company frames this measurement layer around reliability — helping teams know that the skills they depend on work — rather than around monitoring individual users.[1]

History

Lore is developed by Tanagram. The product was publicly available by mid-2026, distributed through a command-line interface and host-application plugins and accessed on the web at lore.link, with the Smart Skill Library introduced as a focused entry point alongside the broader session-sharing platform.[1]

Reception

See also

References

  1. ^ a b c d e f g h i j "Lore". Retrieved 2026-06-16.

Category:Developer tools Category:Artificial intelligence Category:Software companies of the United States

Content Disclaimer

Informasi ini disarikan dari Wikipedia dan disajikan kembali untuk tujuan edukasi. Konten tersedia di bawah lisensi CC BY-SA 3.0. Kami tidak bertanggung jawab atas ketidakakuratan data yang bersumber dari kontribusi publik tersebut.

  1. The information displayed on this website is sourced in part or in whole from Wikipedia and has been adapted for the purpose of restating it. We strive to provide accurate and relevant information, however:
  2. There is no guarantee of absolute accuracy. Wikipedia is an open, collaborative project that can be edited by anyone, so information is subject to change.
  3. It is not intended to constitute professional advice. The content displayed is for informational and educational purposes only. For important decisions (e.g., medical, legal, or financial), please consult a professional.
  4. Content copyright. Wikipedia is licensed under the Creative Commons Attribution-ShareAlike License (CC BY-SA). This means that content may be reused with appropriate attribution and shared under a similar license.
  5. Responsible use. Any risk arising from the use of information from this website is entirely the responsibility of the user.