A code graph for AI coding agents: CodeMesh parses a repository into functions, classes, imports and calls, and serves only the relevant context over MCP to Claude Code, Cursor, VS Code or any MCP client.
OpenScaffold
New· 4Agents for the teams that take customers live: they read calls, emails and tickets, build a cited plan, brief the coding agent and check the work against the customer's rules; free to sign up.
- Artificial Intelligence - AI
- Software Development
- Workflow Management
TrustList summary
Not yet independently verified. Dated from the Y Combinator launch post (16 November 2026, UTC). What the agents do is the maker's own description. No paid prices are published, and the maker's site names no location. We will update this when it can be confirmed, and remove this note.
When a company puts a product into a customer's hands, what the customer said is spread across call recordings, email threads, chat and support tickets. OpenScaffold, a Y Combinator company from the Fall 2026 batch, is built for the forward-deployed, solutions and implementation engineers who have to pull that together before they can build anything.
Five parts
The site describes a Discovery Agent that reads every call, email and ticket as it arrives and keeps the customer's own words findable. A Scoping Agent turns that into a plan in which every requirement cites its source, and flags what has changed or conflicts. A Build Agent is the team's own coding agent, briefed on the customer at the start of each session. A Review Agent checks each change against the rules the customer set, so the team sees what passes before reviewing. Playbooks keep what worked on one deployment as a head start for the next, with the customer's details left out; people approve each one before it is reused.
What it connects to
The site lists Gmail, Outlook, Slack, Teams, Linear, Jira, Notion, Google Drive, GitHub and Granola, with Zendesk, Intercom, Pylon and Confluence mentioned in its FAQ, and calls or transcripts can be uploaded as files. It works with coding agents such as Claude Code, Cursor and Codex, or any agent that speaks MCP.
Team and cost
The launch post says the two co-founders, Rushil and Param, were early employees at a defence technology company where they led deployments for US government contractors. Signing up is free and needs no card. The site shows a pricing page, but paid prices were not published in the pages we read.
Key facts
Maker: Sigma (Y Combinator, Fall 2026) Launched: 16 November 2026 (Y Combinator launch post) For: forward-deployed, solutions and implementation engineers, deployment strategists and leads Connects to: Gmail, Outlook, Slack, Teams, Linear, Jira, Notion, Drive, GitHub, Granola Pricing: free to sign up; paid prices not published Website: openscaffold.ai
Categories & features
- Artificial Intelligence - AI
- Software Development
- Workflow Management
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 11/18/2026
Request a demo or quote from OpenScaffold
Reviews
Write the first review of OpenScaffold
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about OpenScaffold.
OpenScaffold alternatives
Similar listings buyers compare against this one.
Open-source, self-hostable layer that lets a team's coding agents search each other's session histories and talk to each other across laptops and cloud machines; free to start, 100M tokens of sessions a month.
An agent harness that runs hundreds of parallel coding sessions on cloud VMs using the customer's own API keys and subscriptions, with Slack, an API and an app; the maker claims 30 to 80 percent lower cost per task.
Gateway that lets a vendor's AI agents reach a customer's private apps, databases and APIs through one MCP endpoint, with each customer setting what is allowed, what needs approval and what is blocked, and a log of every request.
SDK that finds mistakes production AI agents keep repeating and injects scoped, previewed corrections only in the situations you choose, then measures the effect against held-out sessions, for any agent framework.
Reads coding agents' session logs on the machine to flag leaked credentials and runaway runs, enforces component policies, and can steer or stop an agent; a gateway does the same for customers' agents. Team tier free, 200 session hours a month.
Open-source database and workspace where AI agents and people keep records, docs, skills and apps; free tier, paid plans from $10 per seat a month.
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- More Artificial Intelligence - AIBack to the ranked category
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- AI ModelsBenchmark scores and community ratings for every major model.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.