|
Codixing | Code Retrieval Engine For AI Agents
Codixing is a Rust-native retrieval engine for AI coding agents with AST-aware search, dependency graph intelligence, and token-budgeted output.
|
83 % |
|
ctxpilot — Memory engine for AI coding agents
Cut repeated AI coding context with a local memory engine, token analytics, and Claude Code beta hooks.
|
83 % |
|
greplm — Code intelligence that keeps AI agents on budget
greplm gives AI coding agents instant, precise answers from your codebase — using up to 99% fewer tokens. Works with Cursor, Claude Code, Copilot, and any MC...
|
82 % |
|
Tokeasy — Cut your AI coding-agent token bill
Cut your AI coding-agent token bill. Ten drop-in MCP tools for Claude Code, Codex, Copilot, Cursor & OpenClaw — fewer calls, smaller context, same model. On...
|
82 % |
|
trace-mcp — code graph MCP server for AI coding agents
72.7% fewer input tokens to review a pull request — median over 60 merged pull requests in open-source repos we don't own. trace-mcp is a code graph MCP serv...
|
81 % |
|
Throughput Lines of Code Per Day
Reduce agent input tokens by ~75% by skipping codebase rediscovery. Throughput Lines of Code Per Day indexes your workspace inside the VCS and hands agents i...
|
81 % |
|
AI Agent Cost Calculator | What one agent run actually costs
Most calculators price a single API call. Agents make dozens, and each one re-sends everything before it. Model the full loop: context accumulation, tool cal...
|
81 % |
|
codeix — Portable, composable code index
An open format for structured code indexing. Build once with tree-sitter, query anywhere via MCP.
|
80 % |
|
Cogmeta — Loop optimisation for AI coding agents
Loop optimisation for AI coding agents. Talon predicts and serves the right context and steers your agent — same model, fewer turns, measurably less spend. P...
|
80 % |
|
Gortex — code intelligence for your AI coding agent
Gortex indexes a repo into an in-memory knowledge graph and serves it to coding agents over MCP, HTTP, and a web UI. A 21-tool MCP surface (100+ operations),...
|
80 % |
|
Hayvenhurst: the live code graph that tells your agents what to test, send, and skip
Hayvenhurst keeps a live graph of your codebase and puts it to work: run only the tests a change can break, hand AI agents the exact slice of code they need...
|
80 % |
|
🥬 Lettuce — The diet plan for hungry AI
Your coding agent is a glutton — re-reading the same files every session like it's an all-you-can-eat buffet. Lettuce serves it a smaller, smarter plate. Sam...
|
80 % |
|
RWA Debugger — find integration bugs in Robinhood Chain Stock Token code
Scans a repository for known mistakes in Robinhood Chain Stock Token integrations — misapplied corporate-action multipliers, unguarded oracle reads, wrong ne...
|
80 % |
|
IntelOps · Token FinOps for Agentic AI
Token FinOps for agentic AI builders. See where your agents burn tokens, compare models, cut spend by 10x.
|
79 % |
|
Scubiee — Local Code Search for AI Coding Agents
Help AI coding agents spend fewer tokens finding code with local, open-source repository search.
|
79 % |
|
Ragtoolina — 2.6× cheaper AI coding sessions | Ragtoolina
Ragtoolina gives your AI coding assistant semantic context about your codebase. Same answers, 63% fewer tokens. Save thousands on AI coding costs.
|
79 % |
|
llmreceipts — find out where your AI bill actually went
llmreceipts reads the logs your AI coding tools already write and shows you exactly which dollars were wasted — and how to stop it. Read-only. No proxy, no A...
|
79 % |
|
htmlp — Statically enforceable token limits
Statically enforceable token limits for context files. A strict prompt file format and a matching Rust API for agent context and skills.
|
79 % |
|
Engrams – Architecture Graphs for AI Agents
Stop paying the file-reading tax. Engrams embeds interface contracts, code topology, and Git drift into a self-sufficient local architecture graph your AI ag...
|
79 % |
|
Snout · a context gate for AI coding agents
Snout checks every file before it enters your coding agent’s context and holds back lockfiles, generated code, and vendored bundles. Local, free, and measured.
|
79 % |
Detected social media networks