agent.libx.js 0.93.33 → 0.93.34

package/README.md

@@ -1,6 +1,6 @@
 # agent.libx.js
 
-**A coding agent on par with Claude Code — that also runs where Claude Code can't.**
+**A coding agent that matches Claude Code on correctness — then beats it on cost, tokens, and tool-efficiency, and runs where Claude Code can't (sandbox, browser/edge, database).**
 
 By default it's a full-strength terminal coding agent: real disk, real shell, and the same Read/Edit/Grep/permissions/streaming-DX surface you'd expect from Claude Code. The difference is its two host couplings are swappable seams:
 
@@ -11,16 +11,41 @@ So the *same* agent loop also runs **sandboxed** (in-memory VFS, real disk untou
 
 Claude Code is the floor; running isolated, on the edge, or hybrid is the ceiling.
 
+## How it stacks up vs Claude Code
+
+**Correctness parity — efficiency, cost, and reach are the lead.** Hard 7-task coding suite, Sonnet, *denoised* (each task ×3, no lucky run promotes; `SUITE=hard bun compare/run.ts`):
+
+| | agent.libx.js | Claude Code |
+|---|---|---|
+| Correctness | 7/7 | 7/7 — **parity** |
+| Tool-calls | **16** | 28 — **−43%** |
+| Tokens | **69k** | 171k — **2.5× fewer** |
+| Wall-time | **~100s** | 133s — **~25% faster** |
+
+**Cost** (9-task hard suite, USD-metered, vs CC-on-Opus): **$0.49** single-tier Sonnet (**5.4× cheaper**) · **$0.82** three-tier voice/duplex (**3.3× cheaper**) vs CC-Opus **$2.67** — at quality parity (16/18 vs 17/18 passes).
+
+Plus things Claude Code simply doesn't do:
+
+- **Runs where CC can't** — the *same* agent loop runs on real disk, an in-memory **sandbox**, the **browser/edge** (no Node, no `/bin/sh`), or a **database-backed** workspace. Swap the filesystem, not the agent.
+- **Keyless web search, built in** — `WebSearch` works in any deployment with no API key (DuckDuckGo; auto-upgrades to Tavily if you set one). CC's search is Anthropic-server-bound.
+- **Context-safe by default** — a 1 MB `Grep`/`Read`/MCP result is auto-paginated and can't blow the window; buried detail is recovered via a cheap context-isolated `Ask` peek — **~5.3× cheaper and more accurate** than re-fetching, in a head-to-head.
+- **It improves its own efficiency** — an autonomous evolution loop cut its own tool-use **~50% (32 → 15** on the core suite, denoised), self-discovered, not hand-tuned — the same lever behind the efficiency lead above.
+
+*Honest scope:* the win is **efficiency / cost / reach**, not a claim of smarter reasoning — correctness is parity. All figures are denoised and reproducible (see [Eval & compare](#eval--compare)); full boards in [`mind/09-outperform.md`](./mind/09-outperform.md).
+
 ## Quickstart
 
+Point it at your project — no clone needed (requires [Bun](https://bun.sh)):
+
 ```bash
-bun install                 # links wcli (file:), ai.libx.js + libx.js (bun link)
-bun test                    # 34 unit/integration tests (no API key needed)
-ANTHROPIC_API_KEY=… bun examples/run-sonnet.ts   # drive a real model
-bun eval/run.ts             # quantitative eval scorecard (real model)
+export ANTHROPIC_API_KEY=…                              # or OPENAI_API_KEY / GOOGLE_API_KEY / GROQ_API_KEY
+bunx agent.libx.js "find and fix the failing test"      # run once in the current directory
+bunx agent.libx.js                                      # …or open the interactive REPL
 ```
 
-## Use it
+Want a permanent command? `bun add -g agent.libx.js`, then just `agentx` (and `agentx --duplex` for voice). The agent has full real-disk + shell access by default (like Claude Code); add `--sandbox` to work on an in-memory copy instead. See [The `agentx` CLI](#the-agentx-cli) for flags, sessions, and slash commands.
+
+## Use it as a library
 
 ```ts
 import { AIClient } from 'ai.libx.js';
@@ -103,14 +128,24 @@ Full design + threat model + results: [`mind/08-self-evolve.md`](./mind/08-self-
 
 ## Status
 
-**v1 (done):** loop + hybrid tools + Mem/Disk backends + deterministic `FakeAIClient` tests + real-model run. **5/5 pass@1** on the behavioral eval (Sonnet 4.6); the head-to-head started at correctness parity with Claude Code but ~2× the tool calls (≈28 vs 15) — a gap the **self-evolution loop has now closed autonomously**: it drove its own baseline from 32 → 15 tool-calls (denoised over 3 runs) and ties Claude Code in a fresh head-to-head (15 vs 15). **112 tests green.**
+**v1 (done):** loop + hybrid tools + Mem/Disk backends + deterministic `FakeAIClient` tests + real-model run. **5/5 pass@1** on the behavioral eval (Sonnet 4.6); the head-to-head started at correctness parity with Claude Code but ~2× the tool calls (≈28 vs 15) — a gap the **self-evolution loop has now closed autonomously**: it drove its own baseline from 32 → 15 tool-calls (denoised over 3 runs) and ties Claude Code in a fresh head-to-head (15 vs 15). **820+ tests green.**
 
 See [`mind/`](./mind/) for the full vision, architecture, decision journal, roadmap, eval + head-to-head results, the [parity plan](./mind/05-parity.md), and the [self-evolution design](./mind/08-self-evolve.md).
 
-## Eval & compare
+## Develop & evaluate
+
+Hacking on the runtime itself (from a clone):
+
+```bash
+bun install                # links wcli (file:), ai.libx.js + libx.js (bun link)
+bun test                   # 820+ unit/integration tests (offline via FakeAIClient, no key)
+ANTHROPIC_API_KEY=… bun examples/run-sonnet.ts   # drive a real model end-to-end
+```
+
+Eval & head-to-head (real model):
 
 ```bash
 bun eval/run.ts            # behavioral scorecard (our agent over MemFilesystem)
 bun compare/seed-tasks.ts  # materialize task specs into .tmp/tasks/
-bun compare/run.ts         # head-to-head vs Claude Code (needs `claude` CLI)
+bun compare/run.ts         # head-to-head vs Claude Code (needs the `claude` CLI)
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent.libx.js",
-  "version": "0.93.33",
+  "version": "0.93.34",
   "description": "Edge-native AI agent runtime — drives a virtual filesystem via any LLM (ai.libx.js). Same bytes run in node, browser, or edge.",
   "type": "module",
   "main": "./dist/index.js",
@@ -46,7 +46,7 @@
     "node": ">=18"
   },
   "bin": {
-    "agentx": "cli/cli.ts"
+    "agentx": "dist/cli.js"
   },
   "files": [
     "dist",