Tileward / Context
02 · Tileward Context

Stop paying to resend the same conversation.

A long thread gets resent from the top on every turn. Tileward Context keeps the history and hands the model only the part that answers the question being asked — so the answers stay sharp, the bill stops compounding, and you can see exactly which turns and documents it used.

Measured

Our own usage, read off the same dashboard you'd get.

Our own console, our own conversations. You can re-derive yours the same way.

90.7%

of one long-running Claude Desktop thread never resent — 21.6M tokens of 23.8M

69–96%

cut per conversation across Claude Code sessions, median ~79%

A page

is roughly how much gets sent on a typical turn, instead of the whole history — measured across 2,487 of them

89.1%

across every conversation, lifetime — 23.3M saved of 26.1M

Where it pays, conversation by conversation

ConversationClientTokens without Context
cumulative resend
Tokens with Context
actually sent
Never resent
share saved
long-running assistant threadClaude Desktop23.8M2.2M90.7%
agent session · repo workClaude Code516.8k114.4k77.9%
agent session · refactorClaude Code470.6k146.5k68.9%
agent session · skill authoringClaude Code288.0k56.0k80.6%
agent session · debuggingClaude Code194.5k51.1k73.7%
agent session · long reviewClaude Code146.2k6.4k95.7%
agent session · docs passClaude Code123.2k16.2k86.9%

"Tokens without Context" is cumulative across turns, because a client without memory resends the transcript every time. Short threads have nothing to distill.

Throughput

The bill is not the only thing a shorter prompt buys.

A model reads the whole prompt before it writes a token, so a shorter prompt is reading the GPU never does.

Time to the first word
Full 2,048-token context
51 s
Same context, compressed 25×
1.0 s

6.0× the throughput on the same server, same 16 requests, same 128 tokens of output each. Both arms measured twice, under 1% apart between runs.

Quality

Sending less doesn't mean remembering less.

Twelve facts mentioned once each in a long conversation, asked about later, including questions needing two or three of them at once.

Context tokens per question
Whole transcript resent
3,122
With Tileward
103–127

20 of 20 answered either way, and 0 of 20 with no history at all, so the answers were coming from the conversation rather than from what the model already knew.

Routing shared state per agent role, rather than broadcasting it, held fidelity at 0.95 to 1.00 across two multi-agent flows, and the routed agents scored higher on graded answers than the agent given everything. The token saving is not quoted as a ratio yet: prompt caching is not modelled and will shrink it. See the eval, and what it does not show.

Bring your own conversation. The eval behind those figures is one graded test on one synthetic thread, and it is published with its limits. Production is not one thread: the conversations in the table above are live ones, across more than one client, and they keep accumulating. Point Context at something your team actually runs, a long support conversation or a month of agent sessions, and compare against sending the whole thing. The console shows what it pulled in and what it cost, side by side.

Install

Three steps, about two minutes.

The install line needs a key, and the key needs an account — so here is the whole sequence rather than the middle of it. Step one is free and takes a minute.

Create a free account

No card. You get $1 of credit, 2,000 recalls and 100 MB of documents — enough to run a real thread through it.

Start free

Copy your key

Settings → API keys → create. One key works for both the /v1 API and the MCP endpoint.

Point your client at it

One line for Claude Code, a connector URL for Claude Desktop, or a deeplink for Cursor and VS Code.

Signs you in through the browser, so there is no key to copy or paste.

Terminal
claude mcp add --transport http tileward-context \ https://api.tileward.com/mcp/connect
claude mcp login tileward-context
✓ connected

Two endpoints, and the difference is how you authenticate. Browser sign-in uses /mcp/connect. A key in a header uses /mcp. Ask the server what it offers rather than hard-coding a tool list: the roster grows, and list_tools is how you find out.

Pricing

Tileward Context is included with every model plan.

Context is not a separate line on the bill. Every tier on the main pricing table includes it — what changes with the tier is how many recalls you get and how much you can store.

Explore
$0
no card
  • 2K context recalls
  • 100 MB documents
  • 2 keys
  • 7-day audit window
  • 100 requests/min
Build
$39/mo
$390/yr
or $390/yr · 2 months free
$32.50/mo · saves $78
a solo developer · 10× Explore
  • 20K context recalls
  • 1 GB documents
  • 10 keys
  • 30-day audit window
  • 300 requests/min
Most popular
Pro
$149/mo
$1,490/yr
or $1,490/yr · 2 months free
$124.17/mo · saves $298
a small team · 20× Build
  • 400K context recalls
  • 20 GB documents
  • 3 seats · 50 keys
  • 30-day audit window
  • 1,000 requests/min
Team
$349/mo
$3,490/yr
or $3,490/yr · 2 months free
$290.83/mo · saves $698
5 seats · $35 per extra
  • 2M context recalls
  • 100 GB documents
  • 5 seats · 100 keys
  • 1-year audit window
  • No rate limit
Enterprise
Custom
committed use or air-gapped
  • Committed-use pool
  • Storage is your own disk
  • Unlimited seats · SSO + SCIM
  • Retention you set, locally

Or buy Context on its own

If you want the memory without our model. It is an MCP server and does not care which model consumes the context, so it works against Claude, GPT or your own deployment. These are a different ladder from the tiers above — hence the Context prefix.

Context Free
$0/mo
per developer · no card
  • 50 conversations
  • 2,000 recalls / mo
  • 100 MB storage
  • 30-day retention
Context Pro
$12/mo
per developer
  • Unlimited conversations
  • 100K recalls / mo
  • 5 GB storage
  • 1-year retention
Context Team
$50/mo
5 seats min · $10 per extra, pooled
  • Unlimited conversations
  • 1M recalls / mo
  • 50 GB storage, shared
  • Retention for the life of the account
Context Enterprise
Custom
self-hosted
  • Unlimited conversations
  • Unlimited recalls
  • Storage is your disk
  • Air-gapped / on-prem

Storage counts the distilled conversations and uploaded documents, not the raw transcript — which is why it goes further than it looks.

See it on your own thread

Bring us a long conversation.

We'll distill it, compare against sending the whole thing, and show you what it retrieved. Thirty minutes, an engineer, no deck.