AI context specificity compounds on quality and performance. General context layers serve a purpose - but if you are optimising for AI engineering outcomes alone, and not 'ease of company ops/procurement' - bet on us.
https://t.co/uD6ocKjFC3
We're working on making AI agent context simple.
Start with what you have and let the system, agents, and harness improve it; so you can get on with building.
Remote knowledge system + local memory harness that work hand in hand.
We wrote about it here: https://t.co/JIKO22ru54
The ctx| repo is up: https://t.co/kb5eSjq8pn
Open source self-learning context layer for agents.
We're working on the managed version now, so if you're after a simple platform to manage your engineering org context, DM me!
#ai#agents#context
Co-founder @jakubriedl is at the AI Engineer conference in Melbourne tomorrow, speaking about AGENTS.md being the wrong conversation.
We wrote about it here:
https://t.co/JIKO22ru54
#aiengineering#agents#ai#context
The personal memory solution is getting solved in realtime. The org-wide one is a different beast...
Scattered knowledge, no shared learning, different agents and integrations.
This is the problem to solve for us at https://t.co/aZQtGB1u2W
Big week ahead: the group demo for Ctx| now has 15 CTOs signed up... so much to build before we show it off.. and so little time.
Waitlist at 35 - all companies - all solving the context ceiling issue for agents differently.
A system is needed: https://t.co/aZQtGB1u2W
This is why https://t.co/UsMXXY8MWS focuses on the software engineering ontology. The need is there to solve the gap between institutional knowledge and AI agents to reduce babysitting and increase effective agent run time
#ai#agents#engineering#opensource#context #agentharness
A system is needed. An open-source self-learning context system using the right blend of technologies (knowledge graphs, RAG, vector DBs, search). This is our mission.
https://t.co/5V4jsv2qqq
Tip: Be careful with /init. A good mental model is to treat AGENTS(.md) as a living list of codebase smells you haven't fixed yet rather than a permanent configuration.
Auto-generated AGENTS(.md) files hurt agent performance and inflate costs because they duplicate what agents can already discover. Human-written files help only when they contain non-discoverable information - tooling gotchas, non-obvidous conventions, landmines. Every other line is noise.
Beyond what to put in it, there's a structural problem worth naming: a single AGENTS(.md) at the root of your repo isn't sufficient for any codebase of real complexity.
What you actually need is a hierarchy of AGENTS(.md) files - placed at the relevant directory or module level - automatically maintained so that each agent gets context scoped precisely to the code it's working in, rather than a monolithic file that conflates concerns across the entire project.
OpenAI's sunset review on their agent harness efforts was an awesome read. So much detail into the bleeding edge of agent governance within a single repo.
We've written about it and how that relates to multi-repo structures requiring the same rigour: https://t.co/UuWFO5l56h
A bittersweet post, as it marks the transition from https://t.co/OB0c3JVTch to https://t.co/OCUvt6HwQw.
2 years spent radically simplifying APIs for engineers who wanted immediate context where the work was happening: IDEs and their agents.
https://t.co/esBVKQpTbW
2026 is the era of scaling agents. The engineering community need an intelligent and reliable context-tech foundation to build consistently useful fleets of agents on top of.
Our aim is to be synonymous with essential scaling agent infrastructure.
https://t.co/5V4jsv2qqq