@unerr-ai/unerr 0.0.0-beta.4 → 0.0.0-beta.6

package/README.md

@@ -116,9 +116,21 @@ After install, your AI agent automatically connects to unerr via MCP. No config
 
 ## Supported Agents
 
+### Confirmed
+
+Fully tested and production-ready.
+
 ```bash
 unerr install claude-code        # .mcp.json + CLAUDE.md + .claude/skills/ + hooks
-unerr install cursor             # .cursor/mcp.json + .cursor/rules/
+unerr install cursor             # .cursor/mcp.json + .cursor/rules/ + hooks
+unerr install antigravity        # .antigravity/mcp_config.json + .agents/rules/ + .agents/skills/
+```
+
+### In Development
+
+MCP config and basic integration work. Instruction injection, skills, and hooks support varies — contributions welcome.
+
+```bash
 unerr install vscode             # .vscode/mcp.json + .github/copilot-instructions.md
 unerr install windsurf           # .windsurf/mcp.json
 unerr install zed                # .zed/mcp.json
@@ -134,7 +146,7 @@ unerr install github-copilot-cli # .github/mcp.json + .github/copilot-instructio
 unerr install continue           # .continue/config.json
 ```
 
-Works with any MCP-compatible agent. 15 supported out of the box.
+16 agents supported. Works with any MCP-compatible client.
 
 <details>
 <summary>Manual MCP config (any agent)</summary>
@@ -166,6 +178,7 @@ Works with any MCP-compatible agent. 15 supported out of the box.
 - **Convention awareness** — auto-detected naming, structure, and import patterns injected into agent context.
 - **Semantic search** — `semantic_search` finds conceptually similar code even with different naming. `find_similar` discovers related entities by embedding distance.
 - **Business context** — `get_business_context` explains why code exists — purpose, feature area, taxonomy.
+- **Tool adoption nudging** — 5-layer reinforcement system ensures agents consistently use unerr MCP tools over built-in alternatives. Exec nudges, hook interception, instruction-level enforcement, and skill reminders — all automatic, zero config.
 
 ### Compounding (session 2+)
 
@@ -249,7 +262,9 @@ AI Agent (Claude Code / Cursor / VS Code / Windsurf / any MCP client)
     │                   ├── Token budgeter (prevents context rot)
     │                   └── Compression engine (11 strategies, 645+ classifiers)
     │
-    └── CLI hooks ──→ Output compression ──→ Graph-aware prioritization
+    ├── CLI hooks ──→ Output compression ──→ Graph-aware prioritization
+    │
+    └── Tool nudging ──→ 5-layer adoption reinforcement (hooks, exec, instructions)
 ```
 
 One process. Fully local. No API keys. No network calls. No cloud.