obelisk
obelisk is Every past session, subagent, and workflow -- queryable by your agent, browsable by you - tommy0103/obelisk. It is ranked #177 on the AI Radar, in AI agents, first seen 53 days ago and shared in 8 posts (91.9k views).
GitHub - tommy0103/obelisk: Every past session, subagent, and workflow -- queryable by your agent, browsable by you · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation obelisk Public Notifications You must be signed in to change notification settings Fork 51 ( 51 ) Star 692 ( 692 ) You must be signed in to…
What people said about obelisk on X
我们可能从一开始，就把 Agent Memory 想得太复杂了 最近一篇论文《Is Complex Agentic Memory Always Needed?》做了一个很有意思的实验： 不做 Memory Extraction，不做复杂的知识图谱，也不让 LLM 在写入时反复总结、更新记忆 只保留原始对话历史，在需要的时候检索出来，交给 LLM 自己推理 结果呢？ 在 LoCoMo、LongMemEval 等四个 benchmark 的 7 组测试设置中，这套简单的 RAW-RAG 方案拿下了 6 组第一，最多领先对比的最强 Agentic Memory 系统 5.53 分 这恰好也是我们开发 Obelisk 时一直坚持的思路…
— @QuantumTransf, 6 days ago · 688 likes · see the post
又一篇论文开始挑战我们对 Agent Memory 和 RAG 的传统认知了，最近这方面的工作真的不少 前几天分享了 RAW-RAG 这篇论文，相信让不少人印象深刻：仅仅保留原始历史，在需要时检索并交给 LLM 推理，就能击败不少精心设计的 Agentic Memory 系统 而现在，RAGFlow 团队又发表了一篇新论文《Context as Infrastructure》，从另一个角度讨论了同一个问题： 我们真的需要那么复杂的检索架构吗？ 给不了解 RAGFlow 的朋友介绍一下：这是一个在 RAG 领域颇有影响力、工程背景非常扎实的团队，核心成员有深厚的数据库和搜索引擎研发经验，其联合创始人金海也曾主导 Milvus…
— @QuantumTransf, 3 days ago · 374 likes · see the post
这篇论文其实说明，旧的以记忆提取后产物为 source of truth 的 memory 已经过时了，新 memory 范式应当以原始轨迹为 source of truth 如何压缩信息帮助 agent 更好地查询，意识到 unknown unknown 的部分，以及如何对被压缩的信息进行治理，提取出时序取代关系历史链等等，是下一阶段非常非常重要的课题 另一方面是，如何 build 一个好的 harness，来让 agent 高效地开展 research，连接各个来源的历史信息（不仅仅是 agent session！） 我们在 Nowledge Labs 继续探索这一点，通过 AI Now 和基于 Ontology 的…
— @QuantumTransf, 5 days ago · 53 likes · see the post
Alternatives to obelisk
- Z.ai — chief scientist Jie Tang just revealed the training pipeline behind the upcoming GLM-5.5 (32B, 122B, and 256B) during…
- Firecrawl — @firecrawl - Give your AI agents web data and beyond
- dsh-superagent-prototype — DeepSeek open-sourced the design behind its always-on 'Super-agent': no chat window, and reportedly nearly half the…
- REA for Growth — 4,000+ data endpoints, one key.
- Console by Nace.AI — Cloud Inference
- Muse — We've now paid out more than $1M in @muse bug bounties. That includes $300,000 to a security researcher who found the…
obelisk in numbers
- Rank on the AI Radar: #177 of 10402
- Shared in 8 posts by 3 accounts: @QuantumTransf, @dangerm00se
- 91.9k views on those posts
- First seen 53 days ago, last shared 3 days ago
- Pricing seen by AGK Intelligence: open source
- Market: AI agents
FAQ
What is obelisk?
Every past session, subagent, and workflow -- queryable by your agent, browsable by you - tommy0103/obelisk It was first shared on X 53 days ago and is ranked #177 on the AI Radar.
Is obelisk free?
It is open source.
Who shared obelisk?
3 accounts on X, including @QuantumTransf, @dangerm00se, in 8 posts totalling 91.9k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.