The context layer for AI agents
Rangor connects the systems your team already uses — tickets, wikis, repos, files on Google Drive — and packages what matters for the task: what's decided, what's contested, what changed. After you ship, Usage Receipts record which claims helped — so the next package ranks smarter for your team.
Sign up in minutes · connect a source · no credit card
Steward of UCP Open spec at ucpcore.org Fully managed SaaS
The full story lives across tickets, shared drives, wikis, and threads — but your agent only sees what you remember to paste.
Without Rangor
You hunt. You paste. The model fills the gaps.
With Rangor
Open the task. Get the brief.
15× smaller than copying whole threads
One temporal graph across your stack — tickets, code, wikis, and documents on shared drives. Same engine for engineers shipping features, lawyers reviewing contracts, and finance closing the books.
Data sources
Your agents
Glean finds documents. RAG finds similar chunks. Rovo stays inside Atlassian. Rangor assembles the state of the task — permission-filtered, provenance-backed, ready for your agent.
Glean · enterprise search
You ask a question; it returns search results and chat answers. Synthesis stays on you — no task trigger, no structured package for agents.
RAG pipelines
Embeddings retrieve text that looks like your prompt. Stale and current facts rank alike — no decisions, conflicts, or temporal validity.
Atlassian Rovo
AI inside Jira and Confluence. Strong within Atlassian — but not a cross-source context graph with portable output for Cursor or other agents.
Rangor
Open a ticket or issue — no query required. Precomputed temporal graph assembles must-know facts, decisions, conflicts, and context_diff — to Cursor, ChatGPT, Claude, or Sidebar.
| Glean | RAG | Rovo | Rangor | |
|---|---|---|---|---|
| Trigger | User query | User query | Ask in Atlassian | Open task / issue |
| Output | Search results, chat | Text chunks | Chat in Jira/Confluence | Structured UCP |
| Knowledge model | Search index | Vector store | Atlassian data | Temporal graph |
| What changed? | — | — | — | context_diff |
| Conflicts visible | — | — | — | Explicit section |
| Learns from your team | — | — | — | Usage Receipts → warm ranking |
| Agent delivery | API / chat UI | Custom pipeline | Atlassian UI | MCP, Actions, UCP |
What's true now?
Temporal graph with valid-from / valid-to — invalidated facts don't resurface in top results.
What changed since last visit?
context_diff against your last view of the task — not a fresh search every time.
Why was it decided?
Decisions layer with provenance — not buried in comment thread #47.
What contradicts?
Conflicts from graph invalidations stay explicit instead of being merged away.
Search finds documents. RAG finds chunks. Rangor assembles the state of the task — and keeps improving it for your team.
No query required — Rangor starts from your ticket or issue and ranks what matters for this situation: must-know facts, decisions with status, open conflicts.
ACL from every connected source syncs to every package. You never see a fact from a file or page you can't open — filtered per user, not per workspace.
Schema-valid UCP output: each fact cites a source, each source carries a sha256 hash. Disagreements stay visible instead of being merged away.
Usage Receipts record which claims your agent cited. Warm ranking boosts what helped your team — privacy-safe, claim IDs only.
Rangor ships UCP — the open Universal Context Package we steward at ucpcore.org. Portable structure, fully managed SaaS at app.rangor.io.
One JSON document. Predictable sections any agent — or human — can consume. MCP carries access; UCP carries understanding.
Search and RAG start fresh every time. Rangor remembers when you last opened a task and highlights only the delta — new decisions, moved deadlines, resolved conflicts.
Glean and typical RAG can't answer: «what changed since I was here Tuesday?»
You open the ticket again three days later…
context_diff
Real workflows — not generic search. Each story is a task brief Rangor assembles from your connected sources.
Engineering
Before
47 Jira comments, two Confluence pages, a GitHub thread — pasted into Cursor until something sticks.
With Rangor
Ranked brief: signing required, old keys retire Aug 1, one disagreement still open — ~1,200 tokens.
From Jira + GitHub + Confluence
Legal
Before
40-page MSA on Drive. Associate greps for «indemnity» — misses the playbook update from last quarter.
With Rangor
Cap matches playbook v3, CFO exception cited from email thread, two clauses still in redline — sources linked.
From Google Drive + matter tracker + policy wiki
Finance
Before
Close memo quotes July policy. The October revision lives in a Drive comment nobody re-read.
With Rangor
Policy delta surfaced automatically, audit sign-off linked, spreadsheet exception flagged as a conflict.
From Google Drive + approval threads + policy docs
Connect once. Every task gets a ranked, permission-filtered package — in Sidebar, Cursor, ChatGPT, Claude, or the Dashboard. Submit Usage Receipts after you ship so ranking learns your team.
01
OAuth or tokens for the systems your team already uses. Indexing runs in the background from the Dashboard.
02
Temporal graph + ranking engine — no LLM in the ranking loop. Threads become structured UCP with provenance, not embeddings soup.
03
Browser Sidebar, Cursor, ChatGPT, Claude, or Dashboard — same package, same guarantees.
04
Mark which claims your agent used and whether the outcome worked. Warm ranking boosts what helped — claim IDs only, never your document text.
Same engine underneath — including the learning loop from Usage Receipts. Pick how your team loads task context.
Chrome extension side panel on Jira, GitHub, and more. Ranked must-know facts, decisions, and conflicts without leaving the page.
HTTP MCP with OAuth. Ask Cursor to load context for PROJ-123 or owner/repo#42. When the fix ships, send a usage receipt so ranking learns what helped.
{
"mcpServers": {
"rangor": {
"url": "https://mcp.rangor.io/v1/your-team/mcp"
}
}
}OpenAPI Actions with OAuth — users click Sign in in ChatGPT instead of pasting tokens. Ask about a Jira key or GitHub issue and get a structured brief with decisions and sources.
Connect claude.ai Projects to the same OpenAPI schema. Import once from the Dashboard — structured task context without copying threads into the chat.
Connect data sources, set up agent connectors, and monitor indexing — one shared index per organization. Review Usage Receipts and watch warm ranking improve packages over time.
Same token estimator (~4 chars/token). Raw thread = everything you'd paste into the model. UCP = ranked task context with decisions and provenance intact.
15× smaller — with decisions, conflicts, and hashed sources.
| Issue | Comments | Raw thread | UCP |
|---|---|---|---|
| microsoft/vscode#519 | first 200 of 596 | ~18,500 | ~1,200 |
| rust-lang/rust#158622 | 12 | ~4,450 | ~1,450 |
| pallets/flask#5961 | 4 | ~800 | ~700 |
| pallets/flask#5948 | 0 | ~500 | ~330 |
The win grows with thread size: a decade-long discussion collapses ~15× while keeping decisions, conflicts, and provenance. Reproduce with benchmark_context.py or try live at ucpcore.org/try.
No fake logos. Here's what you can verify today.
We steward the open Universal Context Package spec at ucpcore.org — portable format, vendor-neutral protocol.
Rangor is the hosted implementation at app.rangor.io — indexing, graph, ranking, and MCP included.
Every package filtered per user from source ACLs. Fail closed — no data you can't already open.
Usage Receipts improve ranking with claim IDs only — not your document text.
Token savings claims link to public scripts and live demos — try the format yourself.
v0.5.0-beta — features and pricing evolve in the open. Enterprise SLAs on request.
The first question from every security team: «will the AI see data my user can't access?» Rangor's answer is structural — not a policy page.
Relationship-based access control syncs permissions from every connected source. Context packages are filtered per user before delivery.
Every claim links to hashed sources. Temporal graph tracks valid_from / valid_to — contradictions surface instead of hiding.
Hosted at app.rangor.io — connect your sources, we run indexing, graph, and MCP. No servers to provision.
Shared index per organization with per-user visibility. Access audit for compliance reviews.
Rangor is the reference SaaS for UCP — Universal Context Package. Open spec at ucpcore.org; managed context layer at app.rangor.io. Protocol and product, separated on purpose.
For teams evaluating category creation vs incremental search AI.
Category
Search answers a question. Rangor assembles task state — triggered by opening a ticket, not typing a query.
Architecture
Knowledge indexed ahead of time — enables context_diff, conflicts, and fast package assembly. Not on-demand RAG per request.
Flywheel
UCP is open at ucpcore.org. Team-specific warm ranking from Usage Receipts — data moat that doesn't export.
Plain answers to what teams ask before they connect their first source.
No. RAG retrieves similar text chunks for a query. Rangor builds the state of a task from a precomputed graph — what's decided, what's disputed, what changed since your last visit — without you writing a prompt.
Enterprise search answers questions across documents. Copilot summarizes inside one vendor. Rangor connects multiple sources and delivers a structured, permission-filtered package to Cursor, ChatGPT, Claude, or any agent — triggered by the task you opened, not a chat box.
No. Your content is used to build context packages for your workspace. Usage Receipts store claim IDs and outcomes for ranking — not document text.
Rangor is fully managed SaaS at app.rangor.io. Enterprise plans offer dedicated tenant isolation — contact us for deployment options.
Full UCP format, Sidebar, Cursor MCP, ChatGPT & Claude Actions, one data connector (GitHub public or one Jira project), 50 packages per month, and polling sync. Upgrade to Team for all connectors, shared workspace, and unlimited packages.
No. ACLs from Jira, Drive, GitHub, and other sources sync into every package. Context is filtered per user before delivery — fail closed.
Jira, Confluence, GitHub, Gitea, Bitbucket Server, and Google Drive today — with more connectors on the roadmap. Connect in the Dashboard with OAuth or tokens.
When your agent uses a package, you submit a Usage Receipt — which claim IDs were cited, dismissed, and whether the outcome worked. Warm ranking uses those signals inside your workspace only. No document text is stored in receipts; the next package for similar tasks ranks higher on what actually helped your team.
Open the Dashboard → Agent connectors. For ChatGPT: import the OpenAPI schema into a Custom GPT and complete the OAuth wizard. For Claude: import the same schema into a Project and authenticate with a token. Cursor and other IDEs use MCP from the same page.
Universal Context Package — the open JSON format for task context we publish at ucpcore.org. Rangor is the reference SaaS; any agent can consume UCP.
Sign up in minutes — no credit card. Every tier gets the full UCP format; limits are on scale, sources, and team features.
Solo developer
$0
Teams · 3–50 seats
$25 / seat / mo
Security & compliance
$45 / seat / mo
Regulated & large orgs
Custom
Beta pricing (v0.5.0) — limits and tiers may change. Team plan available self-serve; Business SSO and Enterprise deployment on request.
Create a workspace, connect your sources — then wire Cursor, ChatGPT, or Claude from the Dashboard.
Get started