Your AI agent just got
10x smarter.

Stop watching your AI read 47 files to find one function. Savants gives it the answer in one call.

curl -fsSL savants.sh | sh Copied!
Built for engineers who ship to production every day. No API keys. No cloud required.
Scroll
without savants
You: "Fix the auth timeout bug"
Your AI agent:

→ grep -rn "auth" src/ (312 matches)
→ reads auth.js (2,400 tokens)
→ reads middleware.js (1,800 tokens)
→ reads config.js (900 tokens)
→ grep -rn "timeout" src/ (89 matches)
→ reads 4 more files...

12 tool calls. 14,000 tokens. 47 seconds.
Still looking.
You've seen this before.
There's a better way.
with savants
You: "Fix the auth timeout bug"
Your AI agent:

→ semantic_search("auth timeout handling")

auth/tokenRefresh.ts:handleTokenExpiry()
Lines 89-134 | Score: 0.96

1 tool call. 200 tokens. 400ms.
Already fixing it.

What changes when your AI can actually find code.

200 tokens
instead of 14,000. Your AI stops burning context window on grep noise.
400ms
instead of 47 seconds. It finds the right function on the first call.
Confirmed
not hallucinated. Results come from the actual call graph, not text matching.

Grep returns text matches. Savants returns verified results.

Real problems. Solved in seconds.

Three scenarios every developer hits weekly.

semantic_search "Find the function that retries failed payments"
✗ Without savants
grep "retry" → 23 matches across config files, test mocks, comments
✓ With savants ~400ms
handleTransactionWithBackoff() in payment-service.ts:142
callers "What calls this function? Will my change break anything?"
✗ Without savants
grep the function name - miss indirect callers, dynamic imports
✓ With savants ~15ms
7 confirmed callers across 4 services, blast radius = 12 files
file_skeleton "Show me this file's structure without reading 2,000 lines"
✗ Without savants
Read entire file, burn 2,400 tokens on boilerplate
✓ With savants ~85ms
34 functions with signatures, 85 tokens. 28x less.

Every API doc. Already indexed.
Zero setup.

Your AI doesn't need to hallucinate Stripe's API or guess Kubernetes syntax. Savants indexes official documentation so your agent gets the right answer.

without docs
You: "How do I verify a Stripe webhook signature?"

AI: "I think you use crypto.createHmac('sha256', secret)...
actually let me check... maybe it's hmac.update()..."

Hallucinated. Partially wrong. You debug for 20 minutes.
vs
with savants docs
You: "How do I verify a Stripe webhook signature?"

AI → savants docs search stripe "webhook signature"

Resolve webhook signature verification errors
docs.stripe.com/webhooks/signatures
"Use stripe.webhooks.constructEvent(body, sig, secret)"

Correct. From official Stripe docs. Zero hallucination.
Stripe
Kubernetes
React
Next.js
Fastify
PostgreSQL
Redis
Docker
AWS
AWS
Cloudflare

Pre-indexed and free. Plus upload your private docs: 1 credit per 10K tokens.

60 seconds to 10x.

Step 01

Install

One command. 5MB. No dependencies. No API keys. Your code never leaves your machine.

curl -fsSL savants.sh | sh
Step 02

Index

Savants builds a map of every function, every caller, every import. Locally.

savants reindex
Step 03

Done

Your AI agent automatically uses savants instead of grep. Nothing else to configure.

savants search "auth middleware"
We found a real bug in Fastify.

Root cause identified, call chain traced, PR submitted - in 141 seconds. Without savants, the same task took 17 minutes of manual grep and file reading.

Read the case study →

Local tools are free. Forever.

Cloud tools add production intelligence. Pay per call, no commitments.

Error diagnosis

diagnose-error 50 credits

Root cause file + line in 0.7s. Upstream trace, git blame, Slack context.

Example
Input: "PrismaClientKnownRequestError: Foreign key constraint violated on ProcessingJob_userId"
Root cause: sendFailureNotification() at resume-review.activities.ts:838
Upstream trace:
← triggered by generateAIReview() (LLM validation failed)
← triggered by Temporal worker activity
Fix: Verify userId exists before prisma.create()
Confidence: 85% (enriched with Sentry breadcrumbs)
PR risk analysis

pr-risk 20 credits

8-check risk analysis per PR. Blast radius, affected consumers, test gaps.

Example
Input: PR #847 - "Refactor payment retry logic"
Risk: Medium (6/10)
Blast radius: 12 files, 3 services affected
Warnings:
⚠ Removed error retry - was this intentional?
⚠ paymentService.ts has no test coverage for this path
✓ No breaking API changes detected
Impact analysis

diff-impact 10 credits

Full downstream impact analysis across services and modules.

Example
Input: "What breaks if I rename processOrder()?"
Affected: 18 files across 4 services
api-gateway: 3 routes call processOrder()
billing-service: 2 event handlers
notification-service: 1 webhook
12 test files reference this function
Rename safely with these 18 changes.

radar 10 credits

What-did-I-miss digest. Knows when your graph drifts from production.

Example
Input: "What changed in the last 24 hours?"
3 items need attention:
● Sentry: 12 new errors in auth-service (started 3h ago)
● PR #892 merged without review (config change)
● Deployment v2.4.2 healthy (all checks passed)

10 free cloud calls/month. No card required. Start free →

$ savants connect

Works with your tools

Claude Code
Cursor
Windsurf