I Cut my Agent Tokens By 50%
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 92 launches in llm optimization tools — see how it stacks up on momentum and crowding →
130 other launches read as similar to this one →
Details
- External ID
- 50047627
- Source
- HN
- Company
- —
- Product
- —
- Website domain
- —
- Launched
- Oct. 11, 2026
- Cohort
- —
- Upvotes
- 6
- Upvotes percentile
- 0.27
- Tags
- —
Description
This started by watching the built-in tool calls in Claude code. We noticed that a LOT of the time was being spent searching for lines of code with regex. This approach makes sense when you are working in an unknown environment, but we all work inside of some codebase structure and tracking. This took us down the rabbit hole of codebase indexing and led to us building Indexio. Indexio was built to eliminate the time and tokens agents waste rediscovering a codebase. Regex calls return lots of data each time to the context window which causes bloat over time with items that don't really matter. Since codebase work container mostly static files indexing them and quickly getting to data for discovery is what we were trying to solve.Indexio index's the codebase to its internal DB and then returns what is needed via MCP when asked. We ran into some fun issues when trying to force the session to use a tool call for lookups so there is some aggressive tool call logic which attempts to override built-in lookup tools. If something isn't in the index it will just fallback to regex lookups.The whole system is a single binary written in Rust for performance. In our real world testing we are seeing about 50%-60% reduction in token usage compared to the built-in tools, and near instant lookup times compared to multiple seconds for each regex lookup. One place that indexio does come up shorter than then regex is when looking up symbols. We found that most of the agent's work was done looking at strings of words rather than symbols, but if you have a workflow that is heavy in this specific situation just know it may not fit.We opened sourced everything and would love to hear feedback. Huge Shout out to CocoIndex who gave us the inspiration for this idea.https://github.com/IOServicesLabs/indexio
Enrichment
- Niche
- llm optimization tools
- Vertical
- Horizontal
- Function
- Dev tools
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- token optimization tool for ai agents
- Manually corrected
- False
Could you build this?
Yes This is an MCP (Model Context Protocol) tool or developer CLI that provides indexed code search (such as ctags, ripgrep, or tree-sitter AST queries) to replace blunt regex in agent tool calls.
Discussion
5 comments analyzed.
Competitors mentioned: Language server plugins (LSP)
Concerns raised: Unclear value over language server plugins, Whether it only works with Claude Code
Feature requests: VSCode support, Antigravity SDK connection
Competitors
Other products that read as similar to this one — 130 launches clear the similarity bar, closest 8 shown.
Attention rank: #106 of 131 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 339 days after the earliest competitor.
- CodeRLM · hn · 2026-02-11 · 81 upvotes · similarity 0.52
- Semble · hn · 2026-05-03 · 8 upvotes · similarity 0.50
- Semble · hn · 2026-05-17 · 445 upvotes · similarity 0.50
- I nerfed our coding agents on purpose · hn · 2026-06-05 · 27 upvotes · similarity 0.48
- CodeBurn · hn · 2026-04-13 · 112 upvotes · similarity 0.44
- Tilth · hn · 2026-02-09 · 10 upvotes · similarity 0.44
- CS · hn · 2026-02-22 · 15 upvotes · similarity 0.43
- A better way to handoff web bugs to AI agents · hn · 2025-11-25 · 5 upvotes · similarity 0.41
Other launches for this product
- No other launches for this product.