">
Introduction
1 / 35
EF

exploit-forge

Fully autonomous, multidisciplinary exploit development driven by orchestrated AI agents.

A project by The Exploit Intelligence Platform exploit-intel.com 2026
What Is This

Autonomous Exploit Research

Give it a target. Get a verified exploit - lab, code, and documentation included.

The Problem

A skilled security researcher takes days to weeks to analyze a vulnerability, build a test environment, write an exploit, and prove it works. The process is manual, expensive, and doesn't scale.

🤖 What exploit-forge Does

78 AI agents work together - researching the vulnerability, building Docker labs, writing exploit code, and verifying it against both vulnerable and patched targets. Fully autonomous.

The Result

A complete, verified exploit package - working PoC, Docker lab, and technical writeup - delivered in minutes, not weeks. No human in the loop. Nine pipelines cover every domain.

300+
verified exploit labs built, tested, and documented entirely by AI agents
exploit-intel.com/labs
At a Glance

The Scale of exploit-forge

A single TypeScript monorepo that consolidates 9 autonomous security research pipelines, 78 AI agents, and 18,000 lines of tool infrastructure into one unified platform.

9
Pipelines
78
AI Agents
35K
Lines of TypeScript
18K
Lines MCP Tools
11
Docker Images

Each pipeline deploys 6-13 autonomous Claude agents that sequentially execute specialized security research phases - from reconnaissance to verified exploit delivery.

The Problem

The High-Skill Research Bottleneck

Exploit development is one of the most demanding disciplines in security. It requires deep expertise across multiple domains, tools, and architectures - and even the best researchers hit a ceiling.

🧩 Multidisciplinary Complexity

One CVE needs Ghidra and GDB. The next needs WinDbg on a remote VM. The next needs a Playwright browser session. Each demands a different skillset, different tools, different architectures - and hours of debugging to get right.

🦄 The Unicorn Problem

A researcher who can reverse engineer binaries, write ROP chains, pentest web apps, diff Windows patches, AND decompile Android APKs? They barely exist. And even they can only work on one thing at a time.

🌐 Every Stack, Every Framework

The target could be Node, ASP.NET, PHP, Flask, Spring, Rails - any stack. A human researcher might master two or three. The AI reads them all equally, pulling API docs, source code, and framework internals on the fly.

exploit-forge's answer: 78 specialized agents across 9 disciplines. No skill gaps. No context switching. No ceiling.

The 9 Pipelines

Domain-Specific Security Expertise

Each pipeline is purpose-built for a different security domain - from known CVEs to undiscovered zero-days. Same core engine, different specialized agents and tools.

CVEForge
CVE advisory assessment and PoC development. Takes a CVE ID, builds a lab, writes and verifies an exploit.
7agentsProduction
BinForge
Binary exploitation via reverse engineering. Ghidra + GDB analysis, crash collection, ROP chain development.
8agentsProduction
StackForge
Stack overflow analysis with crash + control gates. Must prove EIP/RBP control before exploitation phase.
9agentsTesting
ZeroForge
Zero-day research with fuzz campaigns. AFL++/libFuzzer with coverage feedback and crash triage.
11agentsTesting
WinForge
Patch Tuesday diffing on Windows VMs. WinDbg remote sessions via QEMU/KVM, ghidriff binary analysis.
8agentsActive Dev
LabForge
Exploit QA and cleanup. Normalizes labs, anonymizes artifacts, verifies reproducibility for release.
8agentsActive Dev
ShannonForge
Web application pentesting. 5 vuln types analyzed in parallel with dedicated Playwright browser agents.
13agentsActive Dev
WPForge
WordPress-native plugin/theme exploit research. Audits source code, builds local WP lab, verifies findings.
6agentsNew
APKForge
Android APK assessment. APKTool + JADX decompilation, secret scanning, bounded external validation.
8agentsNew
CVEForge

CVE Advisory to Proof of Concept

Input a CVE ID. Get a verified exploit with Docker lab, PoC code, and documentation.

🔍

Intel

Query EIP, clone repo, identify versions

🧬

Analysis

Read fix diff, trace vuln path

🏗️

Lab Build

Generate Dockerfile, build containers

💥

PoC Dev

Write exploit, test on vulnerable target

Verify

Confirm patch blocks exploit

📝

Report

Synthesize evidence into README

🔎

QA

Quality review of all deliverables

Production ~$2-8 per run 7 Agents Sequential
BinForge

Binary Exploitation

Reverse engineering meets autonomous exploitation. Ghidra for static analysis, GDB for runtime debugging, pwntools for exploit development.

🔬

Intel

Fingerprint binary, enumerate inputs

🗺️

Reverse

Map control + data flow

🎯

Sink

Analyze dangerous functions

🏗️

Harness

Build test harness + lab

💥

PoC

Execute, measure impact

📝

Report

Document mechanics

🔓

Bypass

Attempt patch bypass

🔎

QA

Validate reliability

Production GDB + Ghidra Exploitability Gate
ZeroForge

Zero-Day Research

Discovers unknown vulnerabilities through automated fuzz campaigns with coverage-guided mutation. 11 agents - the most complex pipeline.

🗺️ Surface Mapping

Identify attack surface, entry points, dangerous sinks. Build call graphs and trace data flow from inputs to sinks.

🔎 Variant Hunting

Search for similar code patterns and related CVEs. Find variants of known vulnerability classes in new locations.

🧪 Fuzz Campaigns

Run AFL++/libFuzzer with coverage feedback, ASAN/UBSAN sanitizers. Auto-triage crashes by exploitability.

Testing 11 Agents ~$10-40 per run Coverage-Guided
StackForge

Stack Overflow Exploitation

The only pipeline with built-in quality gates. Must prove a crash before analyzing control, and must prove register control before attempting exploitation.

🔍

Research

Query EIP, identify vuln class and target

⚙️

Env Setup

Configure build tools and dependencies

🏗️

Lab Build

Compile target, build Docker lab

💥

Crash PoC

Prove crash with ASAN or GDB evidence

🎯

Control

Map registers, calculate offsets

Exploit

ROP chains, shellcode, pwntools

Validate

Confirm exploit reliability

📝

Report

Document exploit mechanics

🔓

Bypass

Attempt patch bypass

Testing Crash Gate + Control Gate GDB + pwntools 9 Agents
WinForge

Patch Tuesday Analysis

Every month Microsoft patches hundreds of binaries. WinForge diffs them automatically - finding what changed, why it matters, and whether it's exploitable.

📋

Patch Intel

Identify target KB, acquire binaries

🔬

Diff Analysis

ghidriff binary diffing, function-level changes

🏗️

Lab Setup

Provision QEMU/KVM Windows VM

💥

PoC Dev

Write exploit targeting the diff

Verify

WinDbg remote debugging session

📝

Report

Document patch analysis

🔓

Bypass

Attempt patch bypass

🔎

QA

Validate deliverables

Active Dev QEMU/KVM Windows VMs WinDbg + ghidriff 8 Agents
ShannonForge

Web Application Pentesting

The largest pipeline - 13 agents. Performs a full web application security assessment with 5 vulnerability types analyzed in parallel, each with its own Playwright browser agent.

Phase 1: Reconnaissance

Pre-Recon analyzes source code for attack surfaces. Recon performs full site mapping with Playwright. Two agents feed all five parallel tracks.

Phase 2: Vulnerability Analysis

Five agents run in parallel - SQLi, XSS, Auth Bypass, SSRF, and Authorization Bypass. Each gets its own browser instance.

Phase 3: Exploitation

Only vuln types with confirmed findings proceed to exploitation. Each exploit agent gets a dedicated Playwright session to prove the finding with evidence.

Active Dev 13 Agents 5 Parallel Tracks Playwright Browsers
WPForge

WordPress Security Research

Purpose-built for WordPress plugin and theme vulnerabilities. Audits source code, maps hook and filter dependencies, builds a local WordPress lab, and verifies findings end-to-end.

📥

Intake

Identify target plugin/theme, fetch source

🗺️

Dep Map

Map hooks, filters, AJAX handlers, REST routes

🔍

Code Audit

Security review - sinks, guards, callbacks

🏗️

Lab Build

Docker WordPress + MySQL + target plugin

💥

Exploit

Verify findings against live WP instance

📝

Report

Full writeup with reproduction steps

New WordPress-Native 6 Agents Hook/Filter Mapping
APKForge

Android Application Assessment

Takes an APK file and tears it apart - decompiling with APKTool and JADX, hunting for hardcoded secrets, mapping API endpoints, and validating findings against live infrastructure.

📥

Intake

Fetch APK, validate target

📦

Unpack

APKTool + JADX decompilation

🔑

Secrets

Scan for keys, tokens, credentials

🌐

Endpoints

Map API calls, URLs, backends

🎯

Validate

Test findings against live targets

🏗️

Lab Build

Docker test environment

💥

Exploit

Verify exploitability

📝

Report

Document all findings

New APKTool + JADX 8 Agents Bounded External Validation
LabForge

Exploit QA and Release Prep

The pipeline that makes everything publishable. Takes raw exploit output from other forges - scrubs internal paths, fixes Docker configs, normalizes documentation, and verifies reproducibility.

🐳

Docker Fix

Repair and normalize Dockerfiles

🧹

Scrub

Remove all internal paths and IPs

📄

Generate

Create standardized README and docs

Verify

Build and test from clean checkout

🔧

Audit Fix

Fix issues found in verification

🔎

QA

Quality gate check

🔧

QA Fix

Address QA findings

Final QA

Final release approval

Active Dev 8 Agents Leakage Scrubbing Release-Ready Output
Architecture

Modular Exploitation Framework

Write the engine once. Plug in a new security domain with ~2,000 lines. Every pipeline inherits retry logic, cost tracking, audit trails, and MCP tooling for free.

plugins
CVEForge
7 agents
BinForge
8 agents
StackForge
9 agents
ZeroForge
11 agents
WinForge
8 agents
Shannon
13 agents
WPForge
6 agents
APKForge
8 agents
LabForge
8 agents
PLUGIN INTERFACE
engine
🤖
Claude Executor
Multi-turn conversations, model selection, retry logic
⏱️
Temporal Runtime
Workflow state, retries, heartbeats, persistence
📊
Audit & Metrics
Cost tracking, turn counts, session telemetry
🚦
Claim Gates
Evidence verification, impact validation, false-positive blocking
MCP TOOL LAYER
infra
10 MCP Servers
18,181 LOC
11 Docker Images
Layered hierarchy
177 Prompts
Template engine
REST API
forge-api/
70%
code reuse
A new pipeline is ~5 files and ~2,000 lines. The core engine, MCP tools, Docker base images, prompt system, and audit trail come built in.
Architecture

Execution Flow

One command triggers a cascade - Docker containers spin up, Temporal orchestrates the workflow, Claude agents execute sequentially, and verified deliverables land in the workspace.

⌨️
./forge cveforge start
CLI dispatch + Docker Compose
⏱️
Temporal Workflow
State machine · retries · persistence
🤖
Claude Agent Turns
Multi-turn conversations · MCP tools
🔧
MCP Tool Servers
save_deliverable · run_exploit_test
🐳
Docker Labs
Vulnerable + patched containers
📦
Workspace Deliverables
PoCs · reports · evidence
How It Works

Temporal Workflow Engine

Every pipeline run is a deterministic Temporal workflow - fault-tolerant, resumable, and fully auditable.

🔄 Retry Presets

Production: 5min → 30min backoff, 50 max attempts
Testing: 10s → 30s, 5 attempts
Subscription: 5min → 6hr, 100 attempts

📊 State Tracking

Current phase, completed agents, per-agent cost/turns/duration, advisory warnings, and human review flags - all persisted in workflow state.

⏸️ Resume Support

Workflows pause and resume from the last checkpoint. Workspaces persist by default - use CLEAN=true for fresh runs.

Temporal.io v1.15 PostgreSQL Backend Heartbeat Monitoring
How It Works

Agent Turn Execution

Each agent is a multi-turn Claude conversation augmented with specialized tools. The executor handles retries, cost tracking, and model selection - so agents focus on the security research.

Claude Executor

Manages multi-turn Claude conversations. Handles MCP tool dispatch, streaming responses, retry logic with exponential backoff, spending cap detection, and API error recovery.

Prompt Manager

Template interpolation with {{CVE_ID}}, {{WORKSPACE_PATH}} variables. Include directives for shared partials. 177 prompt template files across all pipelines.

Multi-Tier Models

Small (Haiku) for lightweight tasks, Medium (Sonnet) for standard agent work, Large (Opus) for complex reasoning. Per-agent model selection optimizes cost vs. capability.

Metrics & Billing

Per-agent tracking of turns used, USD cost, and wall-clock duration. Aggregated into workflow summary. Billing cap detection auto-pauses if spending limits are hit.

How It Works

Deliverables & Evidence

Every agent produces deterministic deliverables - markdown reports and JSON decision gates that downstream agents read to decide whether to proceed.

📄 Markdown Reports

  • Intel brief
  • Vulnerability analysis
  • Lab build report
  • PoC verification report
  • Final README

🚦 JSON Gates

  • Exploitability gate (proceed/block)
  • Runtime gate (env ready?)
  • Finding gate (findings sufficient?)
  • Confidence scores + blockers

📦 Workspace Layout

  • source/ - target code
  • lab/ - Docker builds
  • deliverables/ - reports + PoCs
  • artifacts/ - evidence
Technology

MCP Tool Infrastructure

18,181 lines of MCP server code. 10 in-repo servers plus external integrations - all via stdio transport.

Shared Tools

  • save_deliverable
  • write_file + verification
  • run_in_repo
  • run_exploit_test
  • exploit_claim_gate

Pipeline-Specific

  • WinForge: 18 tools (WinDbg, VM SSH, ghidriff)
  • APKForge: 14 tools (APKTool, JADX, secrets)
  • BinForge: 8 tools (GDB, checksec, crash)
  • ZeroForge: 8 tools (fuzz, sanitizer, triage)

External MCPs

  • EIP server (vuln intelligence)
  • Playwright (5 browser agents)
  • Ghidra + GDB agents
  • SharkMCP (packet capture)
Technology

Docker Image Hierarchy

11 Dockerfiles organized as a hierarchy. Shared base image with pipeline-specific layers adding domain tools.

base.Dockerfile

Ubuntu 22.04 + Node.js 22 + Docker CLI + build tools, git, ripgrep, jq, cmake, Python 3

base-jvm.Dockerfile

Base + Java 21 + Ghidra headless - for BinForge and StackForge reverse engineering

Pipeline Layers

  • CVEForge: GDB, strace, pwntools, checksec
  • BinForge: Ghidra, GDB, ROPgadget, capstone
  • ZeroForge: AFL++, libFuzzer, ASAN/UBSAN
  • WinForge: ghidriff, QEMU guest tools

New Domains

  • ShannonForge: Playwright, Chromium
  • APKForge: APKTool, JADX, aapt
  • WPForge: WordPress CLI, PHP, semgrep
  • LabForge: Docker-in-Docker for cleanup
Technology

The ./forge CLI

One unified command interface for all 9 pipelines. Dispatches to per-pipeline bash scripts that handle Docker Compose orchestration.

Commands

  • start - Launch a pipeline workflow
  • stop - Stop containers
  • logs - Tail live workflow output
  • status - Structured run status (--json)
  • workspaces - List workspace dirs

Examples

  • ./forge cveforge start CVE=CVE-2026-28296
  • ./forge binforge start TARGET=/path/to/binary
  • ./forge shannonforge start URL=https://target.com
  • ./forge apkforge start APK=/path/to/app.apk
  • ./forge zeroforge start TARGET_REPO=git://...
CLEAN=true PIPELINE_TESTING=true REBUILD=true WORKSPACE=name
Parallel Execution

ShannonForge: 5 Parallel Tracks

The only pipeline with true parallel agent execution - 5 vulnerability types analyzed simultaneously, each with a dedicated Playwright browser agent.

Recon Phase
pre-recon + recon
Fan Out
Injection
vuln + exploit
XSS
vuln + exploit
Auth
vuln + exploit
SSRF
vuln + exploit
AuthZ
vuln + exploit
Report
evidence synthesis
Infrastructure

Production Deployment

Two dedicated servers - EU and US - run pipelines around the clock. Temporal manages state, Docker isolates execution, and daily encrypted backups protect everything.

🇪🇺
forge-eu
EU exploit-forge server. Runs all pipeline types. OVH dedicated hardware with Docker + Temporal.
91.134.54.218
🇺🇸
forge-us
US exploit-forge server. Parallel capacity for high-volume pipeline runs. OVH dedicated.
15.204.121.195
🌐
eip-app
Application servers running FastAPI + Apache. Serves exploit-intel.com behind Cloudflare CDN.
2 HA app servers + LB
⏱️
Temporal
Workflow engine with PostgreSQL backend. Manages state persistence, retries, and activity heartbeats.
One instance per forge server
🐳
Docker Compose
Per-pipeline compose files orchestrate Temporal worker + exploit-forge container + workspace volumes.
10 compose files · nested Docker
💾
Backups
Daily automated backups to Backblaze B2. GPG-encrypted. Crontab runs at 02:00-03:30 UTC.
B2 + GPG · daily retention
Infrastructure

Automated Provisioning

Two-phase provisioning - install.sh (13 stages, 30-60 min) + setup.sh (6 stages, 10-15 min). From bare metal to fully operational in under 2 hours.

install.sh - 53 KB, 13 stages

  • Base packages + Docker CE + Node.js 22
  • Java 21 + Ghidra + ghidriff
  • QEMU/KVM + libvirt (WinForge VMs)
  • Clone 15+ repos + build all MCP servers
  • Temporal + PostgreSQL + Docker images
  • Windows VM provisioning (ISOs + QCOW2)

setup.sh - 42 KB, 6 stages

  • System tools + Homebrew
  • Systemd services (Paperclip, forge-browser)
  • MCP infrastructure wiring
  • B2 backup system + GPG keys
  • AI tool settings (Claude Code, Codex)
  • Shell config + environment
Quality Assurance

The Exploit Claim Gate

A critical MCP tool that prevents agents from lying about exploit success. Compares the claimed impact against actual evidence and downgrades or blocks inflated claims.

Claimed Impact

Agent claims "RCE achieved" or "authentication bypass confirmed" based on its analysis and PoC execution results.

Evidence Check

Gate compares claim against actual exploit test output - exit codes, signals, stdout/stderr, timeout state. Does the evidence support the claim?

Verdict

Approved - evidence matches claim.
Downgraded - partial evidence, reduced severity.
Blocked - no supporting evidence.

The Platform

exploit-intel.com

The public face of the Exploit Intelligence Platform - vulnerability search, exploit rankings, stats dashboards, labs, and an MCP server for AI integration.

Exploit Intelligence Platform
BlogStatisticsLabsCLI ToolMCP ServerAPI Docs
Updated 2h ago
339,495
CVEs Tracked
53,335
With Exploits
4,748
Exploited in Wild
1,551
CISA KEV
3,948
Nuclei Templates
49,233
Vendors
42,833
Researchers
Search vulnerabilities...
Search
Severity: All Has Exploits KEV Only EPSS > 0.7
CVE-2026-24289 CRITICAL
Windows Kernel IOCP Race Condition - Use After Free
CVE-2026-3910 CRITICAL
V8 Maglev JIT Type Confusion in Chrome
CVE-2026-4105 HIGH
systemd-machined D-Bus Privilege Escalation
Statistics /stats
CVE Monthly Volume
MCP Server /mcp
17 tools for AI assistants - search vulns, analyze exploits, audit stacks, generate pentest findings
Remote Local Install 17 Tools
Docker Labs /labs
300+ verified exploit labs with Docker environments, PoC code, and technical writeups
12 Stats Charts MCP Server - 17 Tools 7 Theme Options REST API + CLI
Observability

Forge Archive Browser

Every run, every agent turn, every dollar spent - searchable and browsable. Full visibility into what the AI agents are doing and thinking.

Operational Console
Forge Archive Browser
Refresh All Import New
Runs
163
Total Spend
$1279
Artifacts
8,872
Agents
905
Runs 163
CVE-2039-900...BYPASS$4.96
stackforge - Mar 15
CVE-2039-900...BYPASS$2.12
stackforge - Mar 15
vuln-bin$4.81
binforge - Mar 15
Run Detail stackforge - bypass
CVE
CVE-2039-9000002
Duration
12m 15s
Cost
$2.12
Bypass
yes
Status
completed
Overview Agent Story Raw Events Artifacts Bypass
VULN-RESEARCH - ATTEMPT 1
thinking Mar 15, 06:15 PM
Let me start by gathering intelligence on the CVE and examining the source code and binary in parallel.
tool use mcp__eip_server__get_vulnerability
query=CVE-2039-9000002
PostgreSQL Backend 163 Runs Archived Full Agent Replay
Integration

Connected Systems

exploit-forge doesn't operate in isolation - it's wired into the entire Exploit Intel ecosystem. Vulnerability intelligence feeds in, results flow out to the company workflow, and the founder monitors everything from Telegram.

🔍 EIP Server

Query vulnerability intelligence - CVE details, exploit rankings, EPSS scores. Powers the intel phase of every CVE-based pipeline.

📋 Paperclip AI

Company workflow orchestration. CEO and ForgeRunner agents query pipeline status, trigger runs, and monitor progress via forge-ops MCP.

📱 Telegram

Real-time notifications for pipeline phase transitions and completions. The founder monitors runs from their phone.

🐙 GitHub

Clone target repositories, checkout specific commits/tags. SSH key authentication for private repos.

🗄️ PostgreSQL

forge_archive database stores audit logs, agent metrics, and deliverable metadata. Ingested via scripts for historical analysis.

☁️ Backblaze B2

Daily encrypted backups of forge data, audit logs, and workspace artifacts. GPG-encrypted at rest.

Scale

By the Numbers

The scale of what a small team can build when AI agents do the heavy lifting - from a $2 CVEForge run to a $40 zero-day research campaign.

35K
TypeScript LOC
177
Prompt Templates
10
MCP Servers
78
Total Agents
$2-8

CVEForge run cost

$10-40

ZeroForge run cost

2,000

Max turns per agent

Technology Stack

The Full Stack

From TypeScript and Temporal at the core to Ghidra, GDB, and AFL++ at the edges - every tool a security researcher needs, orchestrated by AI.

🦕

TypeScript

ES2022 strict mode

⏱️

Temporal.io

v1.15 workflows

🤖

Claude SDK

v0.2.38 agent runtime

🐳

Docker

11 images · Compose

🔧

MCP

18K LOC · 10 servers

🔬

Ghidra

Headless analysis

🐛

GDB

Runtime debugging

🔨

AFL++

Coverage fuzzing

Results

Real-World Impact

exploit-forge doesn't just generate reports - it finds real vulnerabilities and produces verified, reproducible exploit code.

300+
Verified Exploit Labs
76
CVEs with Published PoCs
0‑days
Found by AI Agents
8
Embargoed CVEs Pending
<75m
Vendor Patch Bypass Time
exploit-intel.com/labs exploit-intel.com/blog github.com/exploitintel/eip-pocs-and-cves
Results

Highlight Reel

A selection of findings - from Windows kernel exploits to vendor patch bypasses in under 75 minutes.

Windows Kernel Use-After-Free

0-day

IOCP race condition in the Windows kernel. WinForge identified the vulnerability through binary diffing of Patch Tuesday updates, then built a working exploit on a QEMU/KVM Windows VM.

CVE-2026-24289

V8 JIT Type Confusion

Patch Bypass

Type confusion in Chrome's Maglev JIT compiler. After the vendor patched the original finding, exploit-forge's bypass agent found a way around the fix - in 75 minutes.

CVE-2026-3910

systemd Privilege Escalation

Patch Bypass

Local privilege escalation via D-Bus in systemd-machined. The vendor's patch was incomplete - exploit-forge identified and bypassed it in 72 minutes, autonomously.

CVE-2026-4105

nginx Protocol Desync

0-day

Previously unknown FastCGI protocol desynchronization bugs in nginx, discovered by ZeroForge through automated coverage-guided fuzzing with AFL++ and sanitizer feedback.

ZeroForge Discovery
Summary

What Makes exploit-forge Special

Four architectural decisions that make the difference between a proof-of-concept and a production system.

🔀
70% Code Reuse
Shared core framework - bug fixes and improvements apply to all 9 pipelines automatically
⏱️
Fault-Tolerant Orchestration
Temporal workflows with retries, persistence, and resume - pipelines survive crashes and recover automatically
Deterministic Evidence
Every exploit is verified against both vulnerable and patched targets - claim gates prevent false positives
🌐
9 Security Domains
CVEs, binaries, web apps, Windows patches, zero-days, WordPress, Android APKs - one platform, one CLI
Closing

Autonomous Security Research

78 AI agents across 9 specialized pipelines - from CVE advisory to zero-day discovery - orchestrated by Temporal, powered by Claude, delivering verified exploit research at scale.

Monorepo
Single source of truth
Temporal
Fault-tolerant workflows
MCP
Tool-augmented agents
9 pipelines · 78 agents · 35K LOC · 18K MCP
One CLI. One monorepo. Autonomous exploit research.
A project by The Exploit Intelligence Platform