One context.
Every agent.
Your team's context, structured once. Every coding agent gets the rules file it expects — in the right format, at the right path, always current.
Specs drift.
Rules rot.
Agents ship the gap.
Context scatters across tools. Each agent reads only its own rules file — and only some of the time.
"The space between what a team knows and what an agent knows is where every project fails."
- Wiki page× Never reaches the agent
- Chat thread× Lost after 14d
- One-off prompt× Vanishes on refresh
- Shared doc× Read by humans, not agents
From repo to every agent.
Your team in the loop.
Connect once. AI flags the gaps, your team fills them in, the CLI ships the result.
Link your repo
The CLI reads your repo locally and builds a structured context. Your source never leaves your machine.
AI surfaces the gaps
ContextHub reviews what it can't infer from your repo and queues targeted questions — sharp prompts, not fuzzy chat.
Refine on a call
Co-edit live with your team. Dig deeper on anything unclear using your team's preferred method — ContextHub keeps track of every decision.
Ship with ch sync
One command pushes the latest graph and pulls every agent file — in the format it expects, at the path it expects, never stale.
Two letters.
Every agent.
ch keeps your agents in sync. Push your latest graph, pull agent files, and swap agents — all from the command line.
Write context
as a team.
Non-technical teammates draft, comment, and refine. AI reads alongside and flags anything it needs clarified.
More than a rules file in git.
Six things that make context actually work across your whole team.
Structured, not scattered
Context is organised around the actual parts of your product — extracted from your repo and kept in sync.
AI that asks the right questions
AI reviews your context and only asks where something is genuinely unclear — sharp prompts, not noise.
Efficient by design
Context is compacted before it reaches your agent — fewer tokens, lower cost, same quality. Still human-readable in your repo.
Switch agents in one command
ch agent codex. Old files removed, Codex files downloaded. No stale leftovers.
Restorable snapshots
Every save snapshots the graph. Restore any version. No branches, no merge conflicts.
Repo stays on your machine
Graph builds locally. Only the graph uploads — never your source, never your secrets.
"Replaced four pasted prompts with one graph that updates itself."
— Engineering lead, design partner
- seed-stage startup
- fintech team
- devtools OSS
- research lab
One context. One sync.
Every agent.
Today's agent. Next month's. The one nobody has shipped yet. Every one gets the file it expects.
- 01 context built from your repo, reviewed by AI, kept in sync
- 01 workspace your team writes once, restores anytime
- 01 sync graph up, agent files down, every path
Your code never leaves your machine.
-
Client-side ingest
The graph builds locally. Only it uploads.
-
Encrypted at rest
Per-context keys. TLS 1.3 in transit. No training on your data.
-
RBAC + audit log
Owner / Editor / Viewer. Share-link expiry. Full trail on Team.
-
SOC 2 in progress
Type I targeted for Q4. Private deployment on Enterprise.
Free for solo. Pay when the team joins.
No seat trap. BYO LLM key on every plan.
Free
- 3 contexts, 1 graph each
- 2 collaborators per context
- Bring your own LLM key
- 30-day version history
- Agent-native export for all tools
Pro
- Unlimited contexts & collaborators
- Shared workspace, private graphs
- Full version history + restore
- Markdown + PDF + all agent formats
- Hosted ContextHub AI (no key needed)
Team
- Everything in Pro
- SAML SSO + SCIM
- Audit log + DPA
- Private deployment (VPC)
- Priority support + onboarding
Common Questions
Why not just commit a rules file to git?
You can. Then you do it again for the next agent. Then you forget which one's stale. The graph is the single source — every agent's file falls out of it.
Which agents are supported?
Every coding agent that takes a rules or context file. Adding a new one is a config PR — one YAML per agent — not a release.
Does my code leave my machine?
No. The graph builds locally. Only the graph uploads. Self-host the editor on Team if even that is too much.
How is this different from a wiki?
Wikis are for humans. ContextHub is a graph with confidence scores, targeted questions, and per-agent emit. A wiki doesn't update an agent's rules when you swap agents.
Do you train on my data?
No. Your graph is yours. Bring your own LLM key on Free and Pro and prompts never touch our infra.
What happens if I cancel?
One command exports everything. The CLI keeps working offline against your local graph.