MindForge

# MindForge

**An agentic intelligence framework for Claude Code** — orchestrates multi-agent workflows with governance, memory, and autonomous execution. Production-hardened with true parallelism, streaming SDK, and zero-trust security. Install once, get structured AI-driven development with built-in quality gates.

---

## Latest: v11.3.1

- **v11.3.1 — Packaging hotfix.** Restores the full published payload: every `npx mindforge-cc` install now delivers all 174 slash commands, 73 skills, 154 subagents, and the complete `.mindforge/` framework. (v11.3.0 shipped a too-narrow npm allowlist that silently dropped commands and skills — fixed here, with a tarball regression test so it cannot recur.)
- **v11.3.0 — "Legion".** Imports 154 specialized Claude-Code-native subagents across 10 categories into `.claude/agents/`, fully rebranded and collision-safe. Additive and backward-compatible.

See [CHANGELOG.md](./CHANGELOG.md) for full release history.

## v11.0.0 — Sovereign Stability

MindForge v11.0.0 "Sovereign Stability" is a production-hardening release focused on reliability, performance, and real-world deployment readiness. Key highlights:

- **Memory-safe operations** — LRU-bounded caches, atomic writes, log rotation, and snapshot garbage collection eliminate resource leaks in long-running sessions.
- **True wave parallelism** — Semaphore-based concurrent execution with configurable max concurrency replaces sequential task dispatch.
- **Streaming SDK** — WebSocket event streaming, `streamExecution()` with AsyncIterable, and `batchExecute()` for high-throughput integrations.
- **Hardened security** — Ephemeral enclave keys, session-scoped agent isolation, time-limited RBAC elevation, dashboard rate limiting, and structured ZK proof returns.
- **Production observability** — `/api/v1/system` health endpoint, P95 latency tracking, heap health monitoring, and real EIS client with retry logic.
- **Graduated intelligence** — Adaptive tier escalation (+1/+2/MAX) with cost-awareness, 3-tier stuck detection, and adaptive context windows.

This release ships 211 personas, 73 skills, 154 specialized subagents, 174 commands, 18 pillars, and 49 swarm templates across 12 engineering domains.


## Installation & Setup

### 🔌 Claude Code Plugin (fastest)

Install MindForge's commands, subagents, and skills directly from the marketplace —
no project files written:

```bash
/plugin marketplace add sairam0424/MindForge
/plugin install mindforge@mindforge
```

Prefer just a slice (e.g. Python agents)? Install a focused pack like
`mindforge-lang@mindforge` instead. See [docs/plugin-installation.md](docs/plugin-installation.md)
for all 11 plugins, token-budget guidance, and team setup.

### 🚀 Quick Start (npx — full framework engine)

The npx installer also writes the complete `.mindforge/` engine (governance, memory,
planning) into your project:

```bash
# For Claude Code
npx mindforge-cc@latest --claude --global

# For Antigravity
npx mindforge-cc@latest --antigravity --global
```

### 🌍 Global Installation

Enable system-wide `/mindforge` commands for your primary AI coding runtime:

```bash
npm install -g mindforge-cc@latest
```

### 📂 Local Project Setup

Initialize MindForge in an existing repository with specialized agent identities:

```bash
# For Claude Code
npx mindforge-cc@latest --claude --local

# For Antigravity
npx mindforge-cc@latest --antigravity --local
```

---

- **Production Hardening (v11.0.0)** — LRU caches, atomic JSON writes, log rotation, HANDOFF validation, and temporal snapshot GC for crash-safe long-running sessions.
- **True Wave Parallelism (v11.0.0)** — Semaphore-based concurrent wave execution with configurable max concurrency replaces sequential dispatch.
- **Streaming SDK (v11.0.0)** — WebSocket event streaming, `streamExecution()` AsyncIterable, `batchExecute()`, model streaming across Anthropic/OpenAI/Gemini providers.
- **Graduated Intelligence (v11.0.0)** — Adaptive tier escalation (+1/+2/MAX) with cost-awareness, 3-tier stuck detection, and adaptive context windows (10/20/30).
- **Security Hardening (v11.0.0)** — Ephemeral enclave keys, session-scoped ZTAI, time-limited RBAC elevation, dashboard rate limiting (100 req/min/IP), token expiration.
- **Observability (v11.0.0)** — `/api/v1/system` health endpoint, P95 latency ring buffer, heap health monitoring, real EIS client with exponential backoff.
- **Grounded Wave Execution (v9.0.0)** — AutoRunner reads HANDOFF.json wave groups, dispatches tasks with audit tracing, persists progress, and resumes on restart (Pillar XXIV).
- **Model Topology Modernization (v9.0.0)** — All model references updated to the Claude 4.x family: claude-opus-4-7, claude-sonnet-4-6, claude-haiku-4-5 (Pillar XXV).
- **Unified Memory Architecture (v9.0.0)** — Knowledge and graph edges consolidated into SQLite (celestial.db) with FTS5 search. Four JSONL stores replaced by one queryable store (Pillar XXVI).
- **Schema Migration Engine (v9.0.0)** — `_migrations` table with versioned migration tracking and transaction-wrapped bulk imports (Pillar XXVII).
- **Integration Test Chain (v9.0.0)** — 27-assertion end-to-end test suite validating the full execution pipeline (Pillar XXVIII).
- **Sovereign Identity Synthesis (v8.1.1)** — Autonomous `SOUL.md` generation derived from reasoning traces and interaction sentiment (Pillar XIX).
- **Autonomous SRE Layer (v8.2.0)** — Self-healing production reliability engine with reactive sentinel observability and adversarial remediation auditing (Pillars XX-XXIII).
- **Unified Persistence Layer (v8.0)** — Centralized SQLite/FTS5 engine for sub-millisecond reasoning audits and semantic reasoning (Pillar XV).
- **Federated Mesh Synthesis (v8.0)** — Signed knowledge handoffs via MindForge Bundles (`.mfb`) and federated intelligence synchronization (Pillar XVI).
- **Autonomous Skill Evolution (v8.0)** — Self-generating persistent skills from reasoning traces with logic-drift mining (Pillar XVII).
- **Orbital Governance (v8.0)** — Hardware-bound (HSM/Biometric) attestation for high-blast-radius security gates (Pillar XVIII).
- **Post-Quantum Agentic Security (v7.0)** — Lattice-based (Dilithium-5) signatures and ZK-Proof bypasses (Pillar XI).
- **Proactive Semantic Homing (v7.0)** — Autonomous "Intent Hunting" and peer-healing mesh behavior (Pillar XII).
- **Autonomous Resource Harvesting (v7.0)** — Real-time token arbitrage and dynamic task routing (Pillar IX).
- **Neural Drift Remediation (v7.0)** — Semantic density heuristics and automated reasoning recovery (Pillar X).
- **Interactive Temporal Steering (v5.10)** — Full history scrubbing, hindsight state repair, and real-time temporal slider navigation (Pillar VII).
- **AgRevOps Hub (v6.0)** — Dynamic ROI tracking ($100/hr mapping), Milestone Velocity forecasting, and Governance Debt monitoring (Pillar VIII).
- **Sovereign Reason Enclave (v5.8)** — TEE-simulated reasoning isolation with Zero-Knowledge (ZK) Audit Trails (Pillar VI).
- **Multi-Cloud Arbitrage (v5.7)** — Dynamic routing across Vertex AI, Bedrock, and Azure with intelligence-first task affinity (Pillar V).
- **Sentinel Execution (v5.6)** — JIT Binary Runtime Attestation and Zero-Trust Skill Enforcement (Pillar IV).
- **Predictive Agentic Reliability (v5.5)** — Advanced loop detection and self-healing resonance (Pillar III).
- **Dynamic Blast Radius (v5.3)** — Real-time impact analysis and circuit-breaker safety in the federated sync (Pillar II).
- **Semantic Vector Consensus (v5.2)** — FIM v2 with cosine-similarity conflict resolution (Pillar I).
- **Human-Agent Handover (v5.0)** — Nexus State Bundles and mid-wave steering injection.
- **Autonomous FinOps (v4.3)** — Dynamic **C2C** (Confidence-to-Cost) routing.
- **Proactive Equilibrium (v4.3)** — Real-time **Wave Divergence** monitoring and autonomous state recovery.
- **MindForge Nexus (v4.1)** — High-fidelity **ART** (Agentic Reasoning Tracing).
- **Zero-Trust Identity (v4.2)** — DID-signed non-repudiable audit logs with HSM/Enclave support.
- **Global Intelligence Mesh (v4.2)** — Cross-repo knowledge sharing and Ghost Pattern Detection.
- **Context Sharding (v3)** — relevance-dense memory management (40% token savings)
- **Adversarial Synthesis (v3)** — zero-drift logic through red/blue model debate
- **RAG 2.0 (v3)** — automatic semantic shadowing for background pattern retrieval
- **Role personas** — specialised agent modes for each task type
- **Specialized Identities** — custom `/agents/` workspace with enriched `IDENTITY.md` protocols
- **Skills** — just-in-time domain knowledge loaded on demand
- **Wave execution** — parallelism with dependency safety
- **Autonomous Engine** — walk-away execution with steerability
- **Real-time Dashboard** — web-based observability with Temporal Slider
- **Browser Runtime** — headful/headless visual QA and sessions

- **Multi-Model Intelligence** — dynamic routing, adversarial reviews, and deep research (v2)
- **Persistent Knowledge Graph** — long-term memory across all engineering sessions (v2)
- **Self-Building Skills** — automatically capture knowledge from any source into reusable skills (v2)
- **Quality gates** — compliance and security are non-bypassable
- **Audit trail** — append-only history of every action

---

## 🛠️ Configuration & Runtimes

MindForge adapts to your existing engineering environment via runtime flags:

| Runtime | Global Command | Local Setup |
| :--- | :--- | :--- |
| **Claude Code** | `mindforge-cc --claude --global` | `mindforge-cc --claude --local` |
| **Antigravity** | `mindforge-cc --antigravity --global` | `mindforge-cc --antigravity --local` |
| **Cursor** | `mindforge-cc --cursor --global` | `mindforge-cc --cursor --local` |
| **GitHub Copilot** | `mindforge-cc --copilot --global` | `mindforge-cc --copilot --local` |
| **Gemini CLI** | `mindforge-cc --gemini --global` | `mindforge-cc --gemini --local` |

### Advanced Setup Options
- **Combined Runtimes**: `mindforge-cc --runtime claude,cursor