not exposed to the end user (for good measure) but as an in-built tool that codex can call it can do the following: memories/list
memories/read
memories/search
memories/add_ad_hoc_note
TOOLS
-
Codex internal memory API endpoints for managing notes
By
–
-
Run local models with agent harnesses like Codex or Claude Code
By
–
You can run local models at home and use any agent harness like Codex or Claude Code with them https://t.co/e5blwOYytx
— Ahmad (@TheAhmadOsman) 16 juin 2026You can run local models at home and use any agent harness like Codex or Claude Code with them
-
Use Codex to automate busy work and update memory
By
–
here are a few things that you should try to experience the future:
— Vaibhav (VB) Srivastav (@reach_vb) 16 juin 2026
– ask codex to use chrome and automate all your busy work like filling forms, capturing info
– ask it to update memory based on your recent sessions, PRs, artefacts on a project, watch it become better in… https://t.co/wxUxB1VlVRhere are a few things that you should try to experience the future: – ask codex to use chrome and automate all your busy work like filling forms, capturing info
– ask it to update memory based on your recent sessions, PRs, artefacts on a project, watch it become better in -
Origin: Cursor AI’s long awaited Git competitor announced
By
–
Cursor/Graphite’s @TomasReimers just announced Origin @cursor_ai
’s long awaited Git competitor, scalable for agent workloads, extensible with api and mcp, and built in merge conflicts and co failure agent resolution -
Companies without visibility on AI agents, Ent fixes that
By
–
Businesses are running AI agents inside live work environments with zero visibility into what those agents are actually doing.
— AI Highlight (@AIHighlight) 16 juin 2026
Ent fixes that. One platform, full intent coverage, human and AI activity tracked in real time. https://t.co/W7w8hsTTtgCompanies run AI agents in live work environments with no visibility into what these agents actually do. Ent fixes that. A single platform, complete coverage of intents, human and AI activities tracked in
-
LangSmith Fleet: two types of agents and when to use them
By
–
LangSmith Fleet offers two types of agents: General purpose chat / Specialized agents @BraceSproul on why we offer a choice, and when to use each.
-
Databricks introduces Genie One, AI coworker for business teams
By
–
Meet Genie One, the data-smart AI coworker for business teams.
— Databricks (@databricks) 16 juin 2026
There's no shortage of AI assistants for business users. What they lack is an AI coworker that understands the business, knows what data to trust, and can turn answers into action.
Genie One is designed to close… pic.twitter.com/0TVfVY8lFUMeet Genie One, the data-smart AI coworker for business teams. There's no shortage of AI assistants for business users. What they lack is an AI coworker that understands the business, knows what data to trust, and can turn answers into action. Genie One is designed to close
-
Your AI agent auto-logs in as you everywhere
By
–
Your AI agent can now log in as you everywhere, automatically. Here's the problem it solves. Your agent runs on a second Mac, not the laptop you use. That machine isn't logged into anything. So your agent can't act as you until you sign in by hand. Once on your laptop.
-
Increase in spending on coding agents and LLM gateway control
By
–
Like many organizations new to AI, our spending on coding agents has increased quite dramatically over the past few months. A key element of the LLM gateway we are developing (available in private preview right now) is the control of…
-
Get a letter grade for your AI agent in 5 minutes
By
–
Get a letter grade for your AI agent in under 5 minutes! iFixAi is an open-source diagnostic that catches AI operational misalignment before it damages your business. Actions your agent takes that don't match what you intended, designed, or expected. The dangerous part: these