Knowledge catalogue
The new Anthropic managed agents API is basically the Letta API that we've had since a year ago, but closed source and with provider lock-in. They even have read-only memory blocks and memory block sh
big supporter of memories not being locked up in provider silos. we've been through this spiel in all the past hype cycles. The new Anthropic managed agents API is basically the Letta API that we've h
> which is exactly why we believe memory should live outside of model providers open harness = open memory which everyone should want! The new Anthropic managed agents API is basically the Letta API t
Great paper on improving memory for AI agents. NEW paper: Memory Intelligence Agent (MIA) MIA boosts GPT-5.4 by up to 9% on LiveVQA. Quick summary: Most memory-augmented agents treat memory as a stati
For AI agents, when you want every last bit of what is possible, open source is turning out to be the only way Hot take: I can't see any startup building their critical core operations on Claude Manag
Hot take: I can't see any startup building their critical core operations on Claude Managed Agents or any proprietary harness as investable. The past weeks have shown why it's critical to build on top
Auto-generated index of all tools mentioned across the wiki.
arXiv:2609.36457v1 Announce Type: new Abstract: Long-term memory systems turn conversations into short stored notes. A note can keep a user fact while losing evidence about whether the fact still hold
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
Keep your agent harness minimal, folks. This paper from MIT CSAIL shows why. (bookmark it) While being very minimal it looks effective and promising for building self-improving agents. They present JA
arXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the extit{agent loop}, where the LLM is placed in an environment exposing a set of tools, and the LLM has
arXiv:2608.06144v1 Announce Type: new Abstract: Most agent benchmarks evaluate tasks independently and cannot measure whether experience from one task helps with later tasks. Existing self-evolution b
Automated lint: 20 errors, 8743 warnings, 3 info
Automated lint: 26 errors, 6728 warnings, 3 info
arXiv:2606.01138v1 Announce Type: cross Abstract: Agent-memory frameworks - mem0, Letta/MemGPT, Cognee, Zep/Graphiti, MemoryOS, MemTensor - each ship their own SDK, storage layout, and operational voc
arXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f
arXiv:2605.09863v1 Announce Type: cross Abstract: Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confab
arXiv:2605.02199v1 Announce Type: new Abstract: Long-term LLM agents must compress streams of past interactions into persistent memory before future queries are known. Existing evaluations usually mea
arXiv:2604.23878v1 Announce Type: new Abstract: Despite a century of empirical memory research, existing AI agent memory systems rely on system-engineering metaphors (virtual-memory paging, flat LLM s