Skip to content

GravityZenAI/agent-ascend

Repository files navigation

Agent Ascend 🚀

Auto-evolution engine for AI agents — by GravityZenAI.

The agent learns from every interaction, builds a knowledge graph, discovers patterns, creates skills automatically, and evolves its strategies over time. Works with or without LLM — all evolution functions have deterministic fallbacks. Works as an MCP server, CLI tool, or OpenClaw plugin.

🚨 Security

  • ZERO remote sharing — Nothing leaves your machine. Ever.
  • No external API keys — Local SQLite, local embeddings.
  • No telemetry — No tracking, analytics, or phone-home.
  • Works 100% offline after installation.
  • Memory Poisoning Guard — Blocks prompt injection, contradictions, and untrusted memory corruption.
  • Zero Trust model — All external input is sanitized before it touches the database.

See SECURITY.md for the full threat model.

3 Ways to Use

Mode Command Use Case
MCP Server npx agent-ascend-mcp Any MCP-compatible client (Claude, Antigravity, etc.)
CLI npx agent-ascend Testing, debugging, manual interaction
OpenClaw Plugin openclaw plugins install ./agent-ascend Native OpenClaw integration

Quick Start — MCP Server

git clone https://github.com/gravityzenai/agent-ascend
cd agent-ascend
npm install
npm run build
npm run mcp

Add to your MCP client config:

{
  "mcpServers": {
    "agent-ascend": {
      "command": "node",
      "args": ["dist/src/mcp/server.js"]
    }
  }
}

Quick Start — CLI

# Record an experience
agent-ascend remember "Fixed CORS issue in API gateway" --outcome success

# Search past experiences
agent-ascend recall "CORS"

# Get context block for your current task
agent-ascend context "How to fix CORS headers in Express?"

# Check stats and level
agent-ascend stats
agent-ascend level

# Knowledge graph
agent-ascend graph "TypeScript"

# Health check with auto-repair
agent-ascend health

# Export all data
agent-ascend export > backup.json

27 MCP Tools

Core Memory

Tool Purpose
ascend_remember Record a new experience (task + outcome + feedback + session_id)
ascend_recall Search past experiences with triple hybrid search (FTS5 + semantic + graph)
ascend_context Get a pre-formatted context block for your current prompt — the main way to use memory
ascend_knowledge Search the knowledge base
ascend_research Autonomous research: generates queries for failures, saves search results

Evolution Engine (Prepare/Apply Pattern)

Tool Purpose
ascend_evolve Full skill lifecycle via prepare/apply actions (see below)
ascend_review Generate structured review for high-impact experiences
ascend_errors Show error clusters and failure-to-skill candidates
ascend_chains Detect error chains (sequences of co-occurring failures)

Governance & Safety

Tool Purpose
ascend_govern Approve, reject, freeze, rollback, quarantine, archive skills
ascend_guard Anti-hallucination guard — checks experiences before saving
ascend_risk_check Evaluate promotion risk for patterns/skills
ascend_integrity Memory integrity check and anomaly detection

Session & Lifecycle

Tool Purpose
ascend_session Start/end work sessions to group experiences
ascend_level View XP, level, and title
ascend_stats Comprehensive memory statistics and trends
ascend_strategy Strategy learning report with rankings
ascend_synthesis Daily synthesis report with recommendations

Data Management

Tool Purpose
ascend_update Modify an existing experience
ascend_forget Safely delete experiences (protects high-value, confirms bulk)
ascend_consolidate Merge duplicates, prune expired, boost valuable memories
ascend_export Export skills, stats, and level as JSON
ascend_import Import skills from JSON
ascend_warmstart Bulk import experiences from JSON
ascend_import_engram Import from Engram JSON export
ascend_graph Query the knowledge graph for entity relationships
ascend_health Diagnostics: integrity, FTS sync, auto-repair

Evolution Engine — Prepare/Apply Pattern

The evolution engine works in two modes:

Mode 1: Automatic (with local LLM)

If a local LLM is configured, evolution runs autonomously — analyzing failures, proposing skills, and evolving strategies.

Mode 2: Host-Agent Driven (without local LLM) ⭐

When no local LLM is available, the host agent (Claude, Antigravity, etc.) drives evolution through the prepare/apply pattern:

1. Agent calls ascend_evolve action="analyze_failures_prepare"
   → Returns failure data + analysis prompt

2. Agent runs the analysis with its own LLM

3. Agent calls ascend_evolve action="analyze_failures_apply" 
   → Passes the analysis results back

Available prepare/apply actions:

Prepare Apply Purpose
analyze_failures_prepare analyze_failures_apply Research failure patterns
reflect_prepare reflect_apply Idle reflection on recent experiences
gepa_prepare gepa_apply Guided Evolution by Pattern Analysis
review_prepare review_apply Structured review of high-impact experiences

Other evolve actions: propose, activate, deprecate, list, list_needing_evolution, evolve_prepare, evolve_apply

Architecture

┌──────────────────────────────────────────────────┐
│                AGENT ASCEND v3.2                 │
│                                                  │
│  ┌───────────────────────────────────────────┐   │
│  │         27 MCP Tools (tools.ts)           │   │
│  └──────────────┬────────────────────────────┘   │
│                 │                                 │
│  ┌──────────────▼────────────────────────────┐   │
│  │   Evolution Engine (prepare/apply)         │   │
│  │  GEPA · PER · Reflection · Synthesis      │   │
│  │  Strategies · Error Chains · Risk Check    │   │
│  └──────────────┬────────────────────────────┘   │
│                 │                                 │
│  ┌──────────────▼────────────────────────────┐   │
│  │   Governance Layer (v3.0)                  │   │
│  │  Approve · Freeze · Rollback · Quarantine  │   │
│  │  Autonomy Levels · Integrity Monitor       │   │
│  └──────────────┬────────────────────────────┘   │
│                 │                                 │
│  ┌──────────────▼────────────────────────────┐   │
│  │          Memory Layer (SQLite)             │   │
│  │  ┌─────────┐ ┌───────┐ ┌──────────────┐  │   │
│  │  │  Store  │ │ Graph │ │  Knowledge   │  │   │
│  │  │  FTS5   │ │       │ │   Manager    │  │   │
│  │  └─────────┘ └───────┘ └──────────────┘  │   │
│  │  ┌──────────┐ ┌───────────┐ ┌─────────┐  │   │
│  │  │  Search  │ │Consolidate│ │Embeddings│  │   │
│  │  └──────────┘ └───────────┘ └─────────┘  │   │
│  │  ┌──────────┐                             │   │
│  │  │  Guard   │  ← Memory Poisoning Guard   │   │
│  │  └──────────┘                             │   │
│  └───────────────────────────────────────────┘   │
│                                                  │
│  3 Adapters: MCP Server · CLI · OpenClaw Plugin  │
│  3 Modes:    zero · economic · full (LLM usage)   │
└──────────────────────────────────────────────────┘

See ARCHITECTURE.md for deep dive.

LLM Modes (v3.2)

Agent Ascend works in 3 modes depending on LLM availability:

Modo LLM calls/día Comportamiento
zero 0 Todo con fallbacks mecánicos — heurísticas deterministas
economic 50 Solo evolveSkill + gepaGenerate usan LLM (con gating)
full ilimitado Todo usa LLM cuando está disponible

Features:

  • LLM Budget Manager — Daily limit tracking con auto-reset
  • LLM Cache — Respuestas cacheadas en SQLite (7-day TTL)
  • Deterministic fallbacksbuildFailureHeuristic, chooseBestVariant, mutateSkillDeterministically, evolveSkillWithoutLLM, buildWeeklyReflection

Level System

Level Title XP
1-10 🌱 Novice 0-999
11-25 ⚡ Operative 1K-6.2K
26-50 🛡️ Veteran 6.7K-25K
51-100 🏆 Master 25K-100K
100+ 👑 Ascended 100K+

Formula: level = floor(sqrt(xp / 10))

Higher levels unlock more autonomy — at Veteran level, the agent can auto-activate skills. At Master level, it can auto-deprecate and evolve skills.

Session Workflow (Recommended)

1. ascend_session action="start"           → Get session_id
2. ascend_context prompt="current task"    → Get relevant past experiences
3. ... do work ...
4. ascend_remember task="..." session_id=X → Record what happened
5. ascend_session action="end"             → Close with summary

Requirements

  • Node.js ≥ 20.0.0
  • No external services required

Data Location

All data stored locally in ~/.agent-ascend/memory.db (SQLite with WAL mode).

License

Apache 2.0 — © 2026 GravityZenAI

About

Auto-evolution engine for AI agents. SQLite memory, ZERO cloud. MCP-native.

Resources

License

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors