The grounding and memory layer that stops AI coding agents from making things up.
A recorded walkthrough of the real product.
Nella sits between an AI coding agent and your repo. Instead of letting the model guess from training data, it indexes the real codebase: AST-chunked, with a semantic vector index and a BM25 lexical index built from a single chunk pass. The agent searches actual code and gets back file paths, line ranges, and confidence scores. On top of retrieval, Nella keeps a persistent memory: typed assumptions that auto-invalidate when the file they depend on changes, a change ledger, and dependency-drift detection, all surviving across sessions in a local `.nella/` directory.
It ships as three surfaces over one core: an MCP server, a CLI, and an embeddable library. That means it plugs into Claude Code, Cursor, or any MCP-compatible agent without lock-in. Parallel agents can register, claim tasks, and record decisions against shared state, with a challenge-response heartbeat keeping the trust chain intact. A companion benchmark package red-teams agents on capability and safety, including multi-turn prompt-injection scenarios. The hosted MCP runs on GCP Cloud Run behind mcp.getnella.dev.
LLM coding agents don't have a memory problem so much as a grounding problem: they invent imports, forget decisions they made five turns ago, and act on stale assumptions about a schema that changed an hour ago. Bigger context windows just let them hallucinate more confidently.
@getnella/mcpmcp+cliThe published package (v0.2.7): an MCP server plus the `nella` CLI that indexes a repo, then hands grounded search, code context, and multi-agent coordination tools to Claude Code, Cursor, and VS Code.
@usenella/corelibraryThe engine behind everything else: AST-based chunking, hybrid semantic and BM25 search, a dependency graph, and persistent context that tracks assumptions, a change ledger, and dependency drift.
@usenella/apiserviceThe Express REST service exposing workspace, search, validation, context, and auth endpoints, backed by a BullMQ job queue and WebSocket progress updates.
@usenella/benchmarklibraryA suite that runs coding agents (Claude Sonnet/Opus, GPT-4o) against tasks and scores pass rate, constraint violations, scope creep, and cost, plus a prompt-injection detection test across eight attack categories.