Agent Memory in 2026: Circuits, Tiers, Evolution
Three new papers reveal how agent memory silently breaks, how a tiered architecture recovers it, and how models can self-improve without human labels.
Articles Tagged "Open Source"
AI Agent Memory in 2026: 5 Frameworks Ranked
We compared Mem0, Zep, Letta, LangMem, and Cognee on architecture, benchmarks, pricing, and use cases to find the right memory layer for your agent stack.
SAP Acquires Prior Labs in $1.16B European AI Push
SAP buys German tabular AI startup Prior Labs and commits €1B to build Europe's first frontier AI lab, while also acquiring data lakehouse Dremio in a two-front push on structured enterprise data.
Nebius Buys Eigen AI for $643M to Own Inference
Nebius agrees to acquire 20-person MIT inference startup Eigen AI for $643M, betting that optimizing every token per Nvidia chip is the real moat in the AI infrastructure race.
Microsoft Sneaks Copilot Credit Into VS Code Commits
VS Code 1.118 shipped with a one-line PR that defaults Copilot as co-author on every git commit - even with AI features turned off - triggering a developer revolt and a promised revert in 1.119.
LiteLLM Exploited 36 Hours After Vulnerability Disclosure
Attackers hit CVE-2026-42208, a critical pre-auth SQL injection in LiteLLM proxy, within 36 hours of the public advisory - targeting database tables holding API keys for every upstream AI provider.
Nemotron 3 Nano Omni Unifies Vision, Audio, Language
NVIDIA's new open omni model activates 3B of 30B parameters, processes video, audio, and documents in one pass, and delivers up to 9.2x higher throughput than other open omni models.
Cost Efficiency Leaderboard: Best AI Performance Per Dollar
Rankings of AI models by cost efficiency in May 2026, comparing performance per dollar across frontier and budget models. Updated with DeepSeek V4, GPT-5.5, and Kimi K2.6.
Claude Enters the Creative Studio - 9 MCP Connectors
Anthropic releases nine MCP-based connectors embedding Claude directly into Adobe, Blender, Autodesk, Ableton, and five other professional creative tools.
Nemotron 3 Nano Omni
NVIDIA's first open omni-modal model: 30B total / 3B active hybrid Mamba-MoE that processes text, images, audio, and video in a single inference loop, with 9x higher throughput than comparable open omni models.
Mistral Medium 3.5
Mistral's first flagship merged model: a dense 128B with configurable reasoning, vision, and 77.6% SWE-Bench Verified, self-hostable on 4 GPUs.
Mistral Ships Medium 3.5 With Cloud Coding Agents
Mistral releases Medium 3.5, a 128B open-weights model that scores 77.6% on SWE-Bench Verified, and pairs it with asynchronous cloud coding agents in Vibe that open pull requests on GitHub while you are away.
