Zep
Long-term memory for agents, built on temporal knowledge graphs.
Zep maintains durable, time-aware agent memory via its open-source Graphiti engine — facts, relationships and their history — so conversations and tasks can span sessions.
Open-source project
In the news
DeepSeek ships Harness Desktop; the 'everything is a plugin' harness passes 240k stars
DeepSeek releases a macOS and Windows Desktop app for DeepSeek Harness, its open-source agent harness where everything — tools, sub-agents, even the loop — is a plugin. The repo passed 240k stars within three months of its August launch, making it the fastest-growing harness in the field's history.
xAI open-sources Grok Build, its coding agent harness
xAI open-sources Grok Build — a Rust coding agent harness and fullscreen TUI around Grok models — unusually early for a first-party tool. It joins Claude Code, Codex and Gemini CLI as the fourth major first-party harness, now with a fourth open one.
Anthropic launches the Claude Agent SDK
Anthropic open-sources the SDK behind Claude Code — the agent loop, tool use, subagents, memory and hooks — letting developers build their own Claude-powered agents on production rails.
Browser Use tops 50k stars — web agents go mainstream
The open-source library for letting agents drive browsers becomes one of the fastest-growing repos in AI, spawning hosted products and a wave of 'web operator' agents.
Related startups
Letta
Stateful agents with memory, from the team behind MemGPT.
Letta (formerly MemGPT, out of UC Berkeley) builds an agent server with built-in memory, context management and state — letting agents persist, learn and be edited like files rather than living in a chat window.
Mem0
The memory layer for AI apps and agents.
Mem0 (from the EmbedChain team) provides a managed + open-source memory layer that extracts, stores and retrieves user and entity memories across sessions — a standard building block for personalization.
Honcho (Plastic Labs)
User modeling and psychology for agent memory.
Honcho is a user-context and memory server that models what each user knows and wants, so agents can personalize without teams hand-rolling their own user-modeling stack.