anon.li
Let your agent manage private email aliases and encrypted file drops over OAuth MCP
XERJ
Local search engine so coding agents stop reading files one by one
About
Open-source local AI search and agent memory, built in Rust
XERJ is a single static binary that indexes any folder automatically and serves BM25, vector and hybrid search with file:line results. Run `xerj init` to wire it into Claude Code or Cursor as an MCP server plus skill, then `xerj autoindex` a project. Its main use case is reference coding: the agent clones and indexes open-source repos close to the task and searches how they solved a problem before writing code. The project reports a 2.7x cut in output tokens at the same solve rate in its own case study. It also exposes a `/_memory` namespace for agent memory and speaks the Elasticsearch API, so existing clients work. Note: the `--insecure` dev mode disables TLS and auth and is meant for a single user on localhost. Repo: https://github.com/xerj-org/xerj.
Features
- Zero-config autoindex for code, docs, logs and PDFs
- BM25, kNN and hybrid search with file:line results
- One-command MCP server and skill setup for Claude Code and Cursor
- Go-to-definition lookups for agents
- Agent memory namespace
- Elasticsearch-compatible API
- Single static binary, offline lexical embedder by default
Install
Related skills
All skillsRelated articles
All articles7 Tools to Cut Your Coding Agent's Token Bill (2026)
Seven tools that cut Claude Code, Codex and Cursor token usage by compressing shell output, searching code and fetching current docs, with honest caveats.
Codebase Context MCP Tools for Claude Code
I compare Serena, XERJ, Graphicle, Graphify and Vesalius for giving Claude Code codebase context: setup, pricing, license and honest caveats.
Best Memory Tools for Claude Code (2026)
Five tools that give Claude Code memory across sessions, agents and machines, with install commands, honest caveats and when CLAUDE.md is enough.
