Skip to content

Products / Vaelor · running since 2026-02-27

VaelorShows a coding agent what its edit will break.

Code intelligence for coding agents

impact_analysis repo=anatolykoptev/vaelor symbol=ExtractCalls

blast_radius
high
total_affected
56
direct_callers
6 of 29 listed
transitive_callers_count
27
tests_covering_count
19
affected_packages
8
  • cmd/vaelor
  • internal/analyze
  • internal/callgraph
  • internal/codegraph
  • internal/compare
  • internal/explore
  • internal/ingest
  • internal/parser
A real result, summarised: Vaelor asked what changing one of its own parser functions would reach. Run on the public repository, 2026-11-20.
35+
MCP tools
read 2026-11-19 · vaelor.ai
16
languages parsed
read 2026-11-19 · vaelor.ai
223
version tags, latest v1.76.0
2026-02-27 to 2026-11-19, counts releases, not adoption · git tags

Documented: vaelor.ai, the vaelor repository README, releases and git tags, read 2026-11-19.

Vaelor is a self-hosted MCP server that parses 16 languages into a call graph and a knowledge graph, so a coding agent sees callers, blast radius and prior review findings before it edits. Apache-2.0. Site: vaelor.ai. Source: GitHub.

What it does

  • MCP tools for impact analysis, call tracing, semantic search, dead-code detection and PR review (35+ tools, per vaelor.ai on 2026-11-19).
  • A persistent graph on PostgreSQL with Apache AGE. PageRank, community and surprise scores feed review and impact answers.
  • A review memory loop: review_pr stores one verdict per changed symbol from the real GitHub review outcome, and understand returns it on the next call.
  • debug_investigate joins a Prometheus alert, failed Jaeger traces and code symbols into ranked file:function suspects.
  • Hybrid retrieval: BM25F, 768-dimension pgvector embeddings, one-hop graph expansion and a reranker.

Status

First commit 2026-02-27, in active development. The latest release on 2026-11-19 is v1.76.0, after 223 version tags: that counts releases, not adoption.