Featured
10xGraph 1.0: the backend your AI agent needs before it ships to customers
10xGraph 1.0 is out: open-source, self-hosted infrastructure for AI apps with auth, roles, tenant isolation, durable state, jobs and tracing, from one CLI.
10xGraph blog
Engineering notes from the 10xGraph team on production AI agents: replay-safe tools, two-tier memory, auth, deployment and release news.
The blog has three kinds of posts. Tutorials build one real use case from an empty folder, with working code that was run before it was published. Engineering notes explain how 10xGraph behaves when things go wrong: a process killed mid-tool, two runs on one thread, a hung node, a stale cache. Release posts say what changed in a version and how to upgrade.
It is written for Python developers who are moving an agent from a demo to a service other people depend on, and for the platform engineers who run it. Every version is listed in the changelog. For reference material, use the docs.
Featured
10xGraph 1.0 is out: open-source, self-hosted infrastructure for AI apps with auth, roles, tenant isolation, durable state, jobs and tracing, from one CLI.
How 10xGraph keeps handoffs, tool visibility, tool results and interrupt resumes under the graph's control, so a steered model cannot walk around a human approval.
When an AI run belongs in a request and when it belongs in a job, and how 10xGraph runs jobs as a thin TaskIQ layer with a worker, a scheduler and the same auth.
The limits a 10xGraph run has by default: parallel tool cap, run, node and tool timeouts, per-user run cap, one run per thread, request size limits and paging caps.
What 10xGraph keeps out of logs, traces and Sentry: hashed user ids, redacted Redis URLs, tool error references, escaped client values and generic errors in production.
What auditors ask of an AI backend, which controls 10xGraph supports in software, and which stay with your organization. Includes a short team checklist.
How fetch_url and client-supplied media links are limited to public addresses in 10xGraph: pinned connections, checked redirects, MediaFetchPolicy and a pre-run 400.
Follow one request through 10xGraph: API server, access control, data and state, background jobs, observability and deploy. What you write and what runs for you.
What 10xGraph runs around your agent by default, the config that turns each protection on, what 1.0 adds, and the honest list of what stays your job.
How 10xGraph keeps users and tenants apart for teams shipping AI to their customers: verified identity, roles with reach, 404 outside reach and tenant columns.
Gate pull requests on what an AI agent did: which tools it called and with what arguments. Uses 10xGraph eval sets, trajectory scoring with no judge model, and pytest.
Cheaper models, a stateless MCP spec, MCP CVEs, approvals everywhere and EU transparency rules: what changed in AI in 2026 and the 10xGraph code to handle each one.
Agentflow is now 10xGraph. Why we renamed it, what it is (self-hosted infrastructure for AI applications), what stays the same in your code, and the honest gaps.
Why a crash mid-node re-runs tools that already fired, why the usual fixes fall short, and how 10xGraph's tool ledger and versioned writes close the gap.
How PgCheckpointer splits agent state between a Redis hot cache and versioned Postgres history, keeps them consistent, and behaves when either one fails.