Skip to content

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

release: 0.18.0

Shrish Dwivedide8456e892ba
diff --git a/CHANGELOG.md b/CHANGELOG.md
index dc547dc9..bd845ee8 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,21 @@
# Changelog
+## 0.18.0
+
+### Added
+
+- **Trail Brain integration** (#322): graft can build a *brain* from a repo and
+ carry its rules into every `ask` — a two-way link, so retrieval is shaped by
+ the team context a brain accumulates, not the code graph alone.
+- **A brain verifies the checkout before it mines** (#344): graft checks the
+ working copy against the repo a brain expects, so rules are never mined from
+ the wrong tree.
+
+### Fixed
+
+- **A brain refreshes its rules from upkeep** (#343), so a single empty pull no
+ longer leaves it stuck without rules.
+
## 0.17.0
### Added
diff --git a/package-lock.json b/package-lock.json
index c18df39a..6c0727d2 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,12 +1,12 @@
{
"name": "@nanonets/graft",
- "version": "0.17.0",
+ "version": "0.18.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@nanonets/graft",
- "version": "0.17.0",
+ "version": "0.18.0",
"hasInstallScript": true,
"license": "MIT",
"dependencies": {
diff --git a/package.json b/package.json
index 03fa2b87..1c801d7f 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "@nanonets/graft",
- "version": "0.17.0",
+ "version": "0.18.0",
"description": "Build a repo's context graph as a folder of linked markdown files: a local, regenerable cache that every query keeps in sync with your code.",
"keywords": [
"ai",