cerebrex 0.9.2 → 0.9.4

package/README.md

@@ -7,20 +7,21 @@
 [![License](https://img.shields.io/badge/license-Apache%202.0-blue.svg)](./LICENSE)
 [![CI](https://github.com/arealcoolco/CerebreX/actions/workflows/ci.yml/badge.svg)](https://github.com/arealcoolco/CerebreX/actions/workflows/ci.yml)
 [![npm version](https://img.shields.io/npm/v/cerebrex.svg)](https://www.npmjs.com/package/cerebrex)
+[![Benchmarks](https://img.shields.io/badge/benchmarks-v0.9.2-brightgreen)](./BENCHMARKS.md)
 [![GitHub Stars](https://img.shields.io/github/stars/arealcoolco/CerebreX?style=social)](https://github.com/arealcoolco/CerebreX)
 [![Issues](https://img.shields.io/github/issues/arealcoolco/CerebreX)](https://github.com/arealcoolco/CerebreX/issues)
 
-**Build. Test. Remember. Coordinate. Publish.**
+**Build. Test. Remember. Coordinate. Publish.**  
 The complete infrastructure layer for AI agents — in one CLI.
 
-[🚀 Quickstart](#-quickstart) · [🗂 Structure](#-monorepo-structure) · [🛣 Roadmap](#-roadmap) · [🐛 Issues](https://github.com/arealcoolco/CerebreX/issues)
+[Quickstart](#-quickstart) · [Why CerebreX](#-why-cerebrex-vs-langchain-crewai-autogen) · [Benchmarks](./BENCHMARKS.md) · [Modules](#what-is-cerebrex) · [Python SDK](#-python-sdk) · [Roadmap](#-roadmap)
 
 </div>
 
 ---
 
-> **Status: v0.9.1 — Security hardening patch: risk gate integrated, JWT auth on token endpoint, KAIROS backoff + validation**
-> `npm install -g cerebrex` — or download a self-contained binary from [GitHub Releases](https://github.com/arealcoolco/CerebreX/releases) (no Node.js required)
+> **Status: v0.9.4 — Security hardening (SSRF protection, security headers, file permissions, KAIROS execution engine)**
+> `npm install -g cerebrex` · `docker pull ghcr.io/arealcoolco/cerebrex` · or download a self-contained binary from [GitHub Releases](https://github.com/arealcoolco/CerebreX/releases)
 >
 > **Live:** Registry UI → `https://registry.therealcool.site`
 > **Live:** Trace Explorer → `https://registry.therealcool.site/ui/trace`
@@ -47,6 +48,56 @@ Eight modules. One CLI. One registry. One coordination layer.
 
 ---
 
+## Why CerebreX vs LangChain, CrewAI, AutoGen
+
+> Full benchmark methodology, raw numbers, and detailed comparisons: [**BENCHMARKS.md**](./BENCHMARKS.md)
+
+### Measured Performance (v0.9.2)
+
+```
+FORGE  parse + scaffold 20-endpoint OpenAPI spec   →   0.12ms  median
+MEMEX  read agent memory index                     →   0.01ms  median
+MEMEX  assemble 3-layer context                    →   0.03ms  median
+HIVE   classify + route 10-task swarm              →   0.09ms  median
+TRACE  record tool-call step                       →  <0.01ms  median  (27,435 ops/s)
+All benchmarks                                     →  100% success rate
+```
+
+### Features No Other Framework Has
+
+| What You Need | CerebreX | LangChain | CrewAI | AutoGen |
+|---------------|:--------:|:---------:|:------:|:-------:|
+| Generate MCP servers from any OpenAPI spec | **FORGE** | ❌ | ❌ | ❌ |
+| Three-layer cloud memory (KV + R2 + D1) | **MEMEX** | ⚠️ Paid | ❌ | ❌ |
+| Nightly AI memory consolidation | **autoDream** | ❌ | ❌ | ❌ |
+| Autonomous background daemon | **KAIROS** | ❌ | ❌ | ❌ |
+| Risk gate on every agent action | **HIVE** | ❌ | ❌ | ❌ |
+| Opus plan + human approval before execution | **ULTRAPLAN** | ❌ | ❌ | ❌ |
+| Built-in MCP package registry | **REGISTRY** | ❌ | ❌ | ❌ |
+| Built-in observability (free, local) | **TRACE** | ⚠️ Paid | ❌ | ❌ |
+| Single CLI for all of the above | `cerebrex` | ❌ | ❌ | ❌ |
+
+### Startup Time
+
+| | CerebreX | LangChain | CrewAI | AutoGen |
+|-|:--------:|:---------:|:------:|:-------:|
+| CLI / module cold start | **~80ms** | ~2,100ms | ~3,400ms | ~1,800ms |
+
+> CerebreX starts **26x faster** than LangChain and **42x faster** than CrewAI.  
+> Bun runtime + single bundled file vs Python's large import tree.
+
+### What the Others Don't Have
+
+**LangChain** is a composition library — it connects existing tools but ships zero infrastructure. Memory requires external Redis/Postgres. Observability requires paying for LangSmith. There's no risk gating, no background daemons, and no MCP generation.
+
+**CrewAI** orchestrates agents in crews but its memory is SQLite-only and in-process. There's no cloud persistence, no risk classification, and no autonomous daemon. Each agent does what it's told — nothing more.
+
+**AutoGen** excels at multi-agent conversation but everything runs in-process. No cloud memory, no background loop, no registry, no observability beyond print statements.
+
+**CerebreX** is purpose-built agent infrastructure: the CLI, the cloud workers, the memory layer, the coordination engine, the observatory, and the package registry — all designed together, all open source, all running on Cloudflare's free tier.
+
+---
+
 ## ⚡ Quickstart
 
 ```bash
@@ -54,6 +105,16 @@ npm install -g cerebrex
 cerebrex --help
 ```
 
+Or via Docker (no Node.js or npm required):
+
+```bash
+docker pull ghcr.io/arealcoolco/cerebrex
+docker run --rm ghcr.io/arealcoolco/cerebrex --version
+
+# Mount a local directory to access spec files, configs, etc.
+docker run --rm -v "$HOME/.cerebrex:/root/.cerebrex" ghcr.io/arealcoolco/cerebrex test run
+```
+
 Or build from source (requires [Bun](https://bun.sh)):
 
 ```bash
@@ -333,6 +394,136 @@ The CerebreX registry includes a browser-based UI served directly from the Worke
 
 ---
 
+## 📊 Benchmarks
+
+Full results with competitive analysis: [**BENCHMARKS.md**](./BENCHMARKS.md)
+
+```bash
+# Run all local benchmarks (no network needed)
+cerebrex bench
+
+# Run a specific suite
+cerebrex bench --suite forge    # MCP server generation
+cerebrex bench --suite memex    # three-layer memory
+cerebrex bench --suite hive     # swarm coordination + risk gate
+cerebrex bench --suite trace    # observability recording
+cerebrex bench --suite registry # package search
+
+# Or run directly with Bun
+bun benchmarks/forge-bench.ts
+bun benchmarks/memex-bench.ts
+```
+
+Benchmarks use `performance.now()`, report **p50/p95/p99 latency** and **throughput (ops/s)**, and run with warmup iterations discarded. CI runs the full suite weekly (Sundays 02:00 UTC). All results in [`benchmarks/results/`](benchmarks/results/).
+
+---
+
+## 🐍 Python SDK
+
+```bash
+pip install cerebrex
+```
+
+```python
+import asyncio
+from cerebrex import CerebreXClient
+
+async def main():
+    async with CerebreXClient(api_key="cx-your-key") as client:
+        # Write to agent memory
+        await client.memex.write_index("my-agent", "# Memory\n- learned today")
+
+        # Assemble a system prompt from all three memory layers
+        ctx = await client.memex.assemble_context("my-agent", topics=["context"])
+
+        # Search the registry
+        results = await client.registry.search("web-search")
+
+        # Submit a KAIROS task
+        task = await client.kairos.submit_task("my-agent", "fetch",
+            payload={"url": "https://api.example.com/data"})
+
+asyncio.run(main())
+```
+
+See [sdks/python/README.md](sdks/python/README.md) for the full SDK reference including ULTRAPLAN, TRACE, LangChain integration, and CrewAI integration.
+
+---
+
+## 🧪 Agent Test Runner
+
+`cerebrex test` lets you write structured assertions against recorded agent traces — no live model calls needed.
+
+```bash
+# Scaffold a starter spec file
+cerebrex test init
+
+# Run all discovered specs
+cerebrex test run
+
+# Run a specific spec with verbose output
+cerebrex test run my-agent.test.yaml --verbose
+
+# CI mode (JSON to stdout, exit 1 on failure)
+cerebrex test run --ci
+
+# Only run tests tagged "smoke"
+cerebrex test run --tag smoke
+
+# Record a saved trace session as a reusable fixture
+cerebrex test record <session-id>
+
+# List all discovered spec files
+cerebrex test list
+
+# Inspect a spec file
+cerebrex test show my-agent.test.yaml
+```
+
+**Spec format** (`my-agent.test.yaml`):
+
+```yaml
+name: My Agent Tests
+
+tests:
+  - name: search tool called with correct query
+    steps:
+      - type: tool_call
+        toolName: web_search
+        inputs:
+          query: "CerebreX agent OS"
+        latencyMs: 120
+      - type: tool_result
+        toolName: web_search
+        outputs:
+          results:
+            - title: "CerebreX — Agent Infrastructure OS"
+        tokens: 45
+    assert:
+      noErrors: true
+      stepCount: 2
+      toolsCalled:
+        tools: [web_search]
+      steps:
+        - at: 0
+          toolName: web_search
+
+  # Replay a recorded trace fixture
+  - name: matches recorded session
+    fixture: my-session.fixture.json
+    assert:
+      noErrors: true
+      stepCount:
+        min: 1
+      output:
+        path: results.0.title
+        contains: "CerebreX"
+```
+
+**Assertions available:** `stepCount`, `tokenCount`, `durationMs`, `noErrors`, `toolsCalled` (with `ordered`/`exact` modes), per-step checks (`type`, `toolName`, `outputPath`/`outputValue`, `latencyMs`), and `output` (dot-path `equals`/`contains`/`matches`).
+
+---
+
 ## 🗂 Monorepo Structure
 
 ```
@@ -340,11 +531,28 @@ CerebreX/
 ├── apps/
 │   ├── cli/              # cerebrex CLI — the main published package
 │   │   ├── src/
-│   │   │   ├── commands/ # build, trace, memex, auth, hive, other-commands
-│   │   │   └── core/     # forge/, trace/, memex/ engines + dashboard
+│   │   │   ├── commands/ # build, trace, memex, auth, hive, bench, test, other-commands
+│   │   │   └── core/     # forge/, trace/, memex/, test/ engines + dashboard
 │   │   └── dist/         # built output (git-ignored, built by CI)
 │   └── dashboard/        # Standalone trace explorer HTML
 │       └── src/index.html
+├── benchmarks/           # Performance benchmark suite (local + live)
+│   ├── forge-bench.ts    # FORGE pipeline timing
+│   ├── trace-bench.ts    # TRACE step recording throughput
+│   ├── memex-bench.ts    # Three-layer MEMEX operations
+│   ├── hive-bench.ts     # Swarm coordination + risk gate
+│   ├── registry-bench.ts # Package search + metadata
+│   ├── agent-tasks-bench.ts  # Cross-framework comparison scaffold
+│   └── src/
+│       ├── stats.ts      # p50/p95/p99 helpers
+│       ├── types.ts      # BenchmarkResult type
+│       ├── reporters/    # console, json, markdown reporters
+│       └── adapters/     # cerebrex adapter (5 standardized tasks)
+├── sdks/
+│   └── python/           # Python async SDK (pip install cerebrex)
+│       ├── src/cerebrex/ # CerebreXClient + module sub-clients
+│       ├── tests/        # pytest test suite with pytest-httpx mocks
+│       └── examples/     # quickstart, langchain_integration, crewai_integration
 ├── workers/
 │   ├── registry/         # Cloudflare Worker — live registry backend + Web UI
 │   │   ├── src/index.ts  # REST API (D1 + KV) + embedded HTML pages
@@ -370,7 +578,10 @@ CerebreX/
 │       ├── deploy-registry.yml # auto-deploy registry Worker
 │       ├── deploy-memex.yml    # auto-deploy MEMEX Worker
 │       ├── deploy-kairos.yml   # auto-deploy KAIROS Worker
-│       └── build-binaries.yml  # build standalone binaries on release
+│       ├── build-binaries.yml  # build standalone binaries on release
+│       ├── benchmarks.yml      # weekly benchmark suite (Sundays 02:00 UTC)
+│       ├── test-python.yml     # Python SDK tests (3.10, 3.11, 3.12)
+│       └── publish-python.yml  # publish cerebrex to PyPI on release
 └── turbo.json
 ```
 
@@ -449,9 +660,9 @@ cd apps/cli && bun run build
 - [x] HIVE swarm strategies — parallel, pipeline, competitive + 6 built-in presets *(v0.9)*
 - [x] `@cerebrex/system-prompt` — master system prompt package + live MEMEX context loader *(v0.9)*
 - [x] Security hardening — risk gate wired into HIVE worker, JWT /token endpoint authenticated, KAIROS exponential backoff + JSON validation, agentId injection prevention *(v0.9.1)*
-- [ ] Agent test runner — `cerebrex test` with replay + assertions *(v1.0)*
-- [ ] Custom domain *(next)*
-- [ ] Enterprise tier + on-prem *(v1.0)*
+- [x] Benchmark suite — p50/p95/p99, forge/trace/memex/hive/registry + cross-framework agent tasks + `cerebrex bench` CLI command *(v0.9.2)*
+- [x] Python SDK — async httpx client, Pydantic v2, full module coverage, LangChain + CrewAI integrations *(v0.9.2)*
+- [x] Agent test runner — `cerebrex test` with replay + assertions, fixture recording, tag filtering, CI mode *(v0.9.3)*
 
 ---