CodeDB Pro cuts that token bill ~97%.
Free graff
is already SOTA on Terminal-Bench. CodeDB Pro keeps the exact same eval scores and gets there in a fraction of the tokens. Your agents just stop dumping whole files into context.
curl -fsSL https://codegraff.com/install.sh | bash
macOS arm64 + Linux x86_64 · zero runtime deps
tokens this task
18,400
5 tool calls · 8.4s wall-clock · Claude / Codex native
same task, same result · hover to
Engineering teams shipping with Codegraff
tokens saved · last 30d
ops · last 7d
per op · codedb p50
outline / lookup
counters from activated installs · speed numbers from bench/ on github · hyperfine, n=10, macOS arm64
The token ledger
One real file, measured three ways. Default tools dump the raw text. codedb, the free engine, reads it structurally. CodeDB Pro lands the exact symbol and edits in kilobytes. The red bar is what you pay for today.
Understand a 2,300-line file
29× leaner than the raw dump
865 tok
with CodeDB Pro
Search the whole codebase
codedb’s search engine ships inside Pro
built in
with CodeDB Pro
Edit one function
Pro only · codedb reads, it doesn’t edit
1.9 KB
with CodeDB Pro
measured · codedb-pro 0.2.9 · same 2,318-line file · "built in" = Pro ships codedb's search engine
How CodeDB Pro works
codedb picks the right file
Most agent failures aren't bad reasoning, they're the agent looking at the wrong file. codedb is graff's retrieval layer: a local index of symbols, outlines, and call paths the agent queries before it acts. SOTA on Terminal-Bench, free, open-source.
CodeDB Pro gets there in ~97% fewer tokens
Same eval scores, a fraction of the footprint. outline returns 47 tokens where a raw read pulls 2,103. symbol lookups land the exact function, never the whole file.
Then Pro edits, symbol-safe
The one thing the free engine can't do. Symbol-safe patches write 1.9 KB where default tools rewrite 169 KB. Immune to line drift, concurrent agents, and mid-session file growth.
What CodeDB Pro adds
Scope mode context, not noise
ripgrep can't do thisEvery match returns its enclosing function. Not a line. Not a file. The exact block your agent needs to act on.
zigrep -S 'validateInput' src/
Structural read 47 tokens vs 2,103
outline firstoutline gives the full symbol map of a file. Then symbol pulls exactly the function, never the whole file.
zigread outline src/main.zig
Symbol-safe patching no line drift
edit by nameEdit by function name, not line numbers. Survives upstream diffs, concurrent agents, and mid-session file growth.
zigpatch --symbol parseToken src/auth.zig
Batch ops 10 reads in 7ms
0.7ms per opPersistent daemon. No fork/exec per call. Reads, searches, diffs, and edits run in parallel over one stdio pipe.
codedb-pro batch [read, search, diff, edit]
Benchmark · same query
6.4× faster
hyperfine · 4.7 GB repo · macOS arm64 · n=10
Pricing
$99/year is one seat. The ledger above is one real file: 25,324 tokens of raw dump down to 865, edits in kilobytes not hundreds. Every week you wait, that gap is tokens you already pay for, spent re-reading files.
Individual
1 seat · $99/seat · all tools, all editors
Team
2 seats · $80/seat · save $38 vs 2 solo seats
Team Plus
5 seats · $69.80/seat · save $146 vs 5 solo seats
Stripe checkout link by email · same-day
Engineering org · 10+ seats
Volume pricing, invoiced annually, MSA on request. One-day turnaround on quotes.
Refund within 14 days · License keys by email · No subscription auto-renew lock-in
Run graff provider login codegraff
and you get instant access to the frontier set. No API keys to manage, no provider accounts to create. Credits start at $10, top up from the dashboard.
CodeDB Pro. One install per engineer. Works with Claude Code, Codex, Cursor, Windsurf. Per-seat licenses, by email.
curl -fsSL https://codegraff.com/install.sh | bash
codedb-pro activate CGPRO-XXXX-XXXX engineer@company.com
codedb-pro mcp register --client claude-code
Runs locally · your code never leaves the machine · uninstall and your agent falls back to its built-in tools
Built by Rach Pradhan · hi@codegraff.com · Terms · Privacy