Skip to main content

Everything Under the Hood

10 entity types, 10 autonomous agents, knowledge graph, Passport identity — everything your AI needs to remember, reason, and get better over time

Claude CodeCursorGitHub CopilotWindsurfOpenAI CodexGemini CLIChatGPT
Claude CodeCursorGitHub CopilotWindsurfOpenAI CodexGemini CLIChatGPT
Claude CodeCursorGitHub CopilotWindsurfOpenAI CodexGemini CLIChatGPT
Claude CodeCursorGitHub CopilotWindsurfOpenAI CodexGemini CLIChatGPT
Codebase Memory

10 Structured Entity Types

Typed, structured memory your AI agents understand and use automatically — not unstructured key-value blobs

Error History

Debug context that persists. Stack traces, root causes, solutions. Your AI won't hit the same bug twice.

Architecture Decisions (ADRs)

Why you chose React over Vue. Why PostgreSQL over MongoDB. Your AI follows the rationale, not just the choice.

Session Context

Pick up where you left off. Your AI knows what you were working on, even after closing the terminal.

Architecture

Your AI understands your stack. Components, technologies, dependencies - all mapped and connected.

Coding Standards

Rules your AI applies automatically. Team conventions, linting preferences, naming patterns.

Code Patterns

Reusable solutions your AI remembers. 'We solved this before' - and your AI knows exactly how.

Tags

Cross-memory labels for organization. Your AI uses tags to find related context across all memory types.

Relationships

Knowledge graph links your AI traverses. 15 relationship types help discover connected context.

Generic Memories

Flexible storage for anything else. Context that doesn't fit other types but matters to your project.

Knowledge Graph
Pro

Connected Codebase Memory

15 relationship types let your AI traverse connections. Error → root cause → fix → prevention.

Relationship Types
implementsreferencessupersedesrelates_tocaused_byresolvesdocumented_independs_onblocksduplicatesvalidatesreproducescontradictsenrichesinforms
AI Graph Traversal

Your AI uses breadth-first search to find related context automatically. No manual linking required.

  • ADR → Errors it caused → Fixes that resolved them
  • Error → Root cause → Prevention pattern
  • Architecture → Coding standards → Code patterns
MCP-Native Integration

Your AI Calls ACE Directly

56 MCP tools your AI coding assistant uses natively. Stores what it learns, retrieves context automatically.

Memory

Store and retrieve with semantic search

ace_remember
ace_recall
ace_get_context

Error History

Debug context that persists

ace_track_issue
ace_resolve_issue
ace_find_solutions

ADRs & Patterns

Capture decisions and code patterns

ace_track_decision
ace_architecture
ace_patterns
ace_best_practices

Graph

Navigate relationships

ace_graph_traverse
ace_graph_connect
ace_graph_related
ace_graph_list

Search

Deep semantic search

ace_search
ace_manage_tags

Session

Session context that persists

ace_log_work
ace_get_stats

Plans

Requirements to structured memory in one call

ace_generate_plan
ace_create_plan

Observer

Proactive error detection and learning

ace_observe
ace_review_observations
ace_trigger_learning

Agents

Background memory maintenance

ace_agent_status
ace_trigger_agent

Namespaces

Multi-project workspace management

ace_list_namespaces
ace_create_namespace
ace_set_namespace
ace_get_current_namespace

Also Includes

  • 9 read-only resources
  • 6 workflow prompts
  • Full MCP compliance
Plans

Requirements to Structured Memory in Seconds

Describe your architecture in natural language. Plans creates ADRs, components, patterns, and coding standards — all linked in the knowledge graph atomically.

1Describe

Enter your requirements in natural language. Add context about your tech stack and constraints.

2Generate

AI creates ADRs, architecture, code patterns, coding standards - all linked with relationships.

3Save

Review the context, then save to memory. Your AI coding assistant now has full project context.

Works with every AI coding tool:
Claude CodeCursorWindsurfGitHub CopilotOpenAI CodexGemini CLIChatGPTVS Code + ContinueAiderZedAny REST-capable tool
MCP-native integration for 7 tools • REST API for universal access • Works with any AI that can make HTTP requests
REST API

Works With Any AI Tool

Full REST API for tools without MCP support. Complete CRUD for all memory types plus semantic search, temporal graph, and hybrid search.

# Store a code pattern
curl -X POST \
  http://localhost:7777/api/v1/my-project/memory \
	  -H "Authorization: Bearer $TOKEN" \
  -d '{"key": "auth-pattern", "value": {"pattern": "JWT with refresh tokens"}}'
# Track an error
curl -X POST \
  http://localhost:7777/api/v1/my-project/issues \
	  -H "Authorization: Bearer $TOKEN" \
  -d '{"title": "Login fails on Safari", "severity": "high", "category": "bug"}'
Semantic Search

Sub-10ms Context Retrieval

True semantic understanding. Your AI finds relevant context even when wording differs. No latency added to your workflow.

Cross-Memory Search

Search across all memory types at once - errors, ADRs, code patterns, architecture.

Error-Solution Matching

"Find similar bugs" actually works. Your AI finds past fixes and applies them automatically.

Context Retrieval

Your AI gets comprehensive context combining ADRs, coding standards, and architecture for any question.

Shared Context for Dev Teams

Your Whole Team's AI Gets Smarter

When one developer's AI learns something, everyone's AI knows it. New team members inherit full codebase context.

Namespaces

Organize by project, team, or purpose. Complete isolation between namespaces.

Role-Based Access

Owner, Admin, Write, Read permissions. Invite by email. Manage from dashboard.

Real-Time Sync

Everyone's AI sees the same context. One developer fixes a bug, everyone's AI learns the solution.

Observer
Pro

Catch Errors Before Production

Observer reviews AI-generated code against your codebase memory. Checks for contradictions with ADRs, violations of coding standards, and known anti-patterns.

Code Review

Automatically scan AI-generated code for errors, anti-patterns, and violations of your coding standards.

ADR Alignment

Check new code against existing architecture decisions and patterns. Detect contradictions before they cause bugs.

Role-Based Analysis

Get feedback from different perspectives - developer, architect, QA, or security. Each role focuses on relevant concerns.

# Review AI-generated code with Observer
ace_observe({
  content: "Generated authentication code...",
  context: "Implementing user login flow",
  role: "security"
})

// Observer checks against your codebase memory
// and returns warnings if it violates ADRs or patterns
Agentic Intelligence
Pro

10 Autonomous Agents

AI agents that observe, reason, act, and reflect on your memory store. Powered by LLM reasoning (Claude, GPT, Gemini), they catch contradictions, surface insights, and maintain data quality autonomously.

Graph Maintenance

Validates and repairs knowledge graph relationships. Fixes broken links, removes duplicates, and reports connectivity stats.

Quality Governor

Validates input quality before storage. Checks completeness, consistency, and ensures new data meets your standards.

Memory Consolidator

Identifies near-duplicate memories and merges them while preserving unique information across all entity types.

Knowledge Guardian

Catches contradictions between memories, ADRs, and patterns. Uses LLM reasoning to detect semantic conflicts humans miss.

Graph Intelligence

Discovers missing links between entities. Suggests connections your AI should know about based on content analysis.

Risk Engine

Surfaces patterns and risks across your memory store. Detects architectural drift, recurring errors, and emerging trends.

Pattern Detector

Detects recurring patterns in work logs, decisions, and issues. Surfaces actionable insights from your project history.

Observer Learning

Extracts patterns from Observer findings. Automatically creates searchable memories from recurring observations.

Session Manager

Tracks session state and ensures smooth context continuity across conversations. Maintains session history.

Decision Recorder

Records decisions with rationale and tracks outcomes for accountability. Ensures important choices are captured.

Observe → Reason → Act → Reflect

Each autonomous agent follows a reasoning loop powered by your choice of LLM. They observe your memory state, reason about what needs attention, take action, then reflect on outcomes to improve over time. Full execution traces let you see exactly what each agent did and why.

Temporal Knowledge Graph
Pro

Time-Aware Memory

Query your knowledge graph at any point in time. See how your architecture evolved, when decisions changed, and what your AI knew on any date.

Point-in-Time Traversal

"What did we know on January 15th?" - traverse the graph as it existed at any point in time with the as_of parameter.

Relationship Versioning

Every relationship change is versioned. See the full history of how connections between entities evolved over time.

Episodes

Group related entities into temporal episodes - work sessions, deployments, code reviews. Track what happened together.

# Query graph state from a specific date
GET /api/v1/my-project/relationships/traverse/decision/42?as_of=2026-01-15T00:00:00Z

// Returns the graph exactly as it was on January 15th
// Relationships added after that date are excluded
Hybrid Search
Pro

Semantic + Graph Intelligence

Combines semantic similarity (0.6 weight) with graph proximity (0.4 weight) for results that understand both meaning and relationships.

Embeddings Everywhere

Embeddings on all 10 entity types. Every memory, decision, issue, and pattern is semantically searchable.

Graph Reranking

Graph distance reranking for context-aware results. Related entities are boosted based on knowledge graph proximity.

Configurable Weights

Tune the balance between semantic similarity and graph proximity for your specific use case.

AI Genome Lab
Founder

The Evolution Layer

Other platforms store memories. ACE3 evolves cognition. Eight behavioral traits that adapt through every interaction.

8 Behavioral Traits

Perception, Reasoning, Empathy, Memory, Expression, Adaptation, Regulation, Integration — each evolves independently.

Agent Specialization

Fork agents with domain-specific behavioral biases. Security reviewers, compliance auditors, creative assistants.

Full Lineage Tracking

See how your AI's behavior evolved over time. Every generation, mutation, and adaptation is recorded.

Live Evolution

Traits activate and mutate in real-time as your AI processes information. Watch your AI develop a unique behavioral signature.

Passport
Pro

Portable AI Identity

Device-bound cryptographic authentication that never expires. Passport stamps track achievements, trust scores grow over time.

Cryptographic Identity

Device-bound keys that uniquely identify your AI agent. No passwords, no tokens to rotate. Hardware-level security.

Trust & Stamps

Passport stamps record achievements and usage milestones. Trust scores grow organically as your AI proves reliable over time.

Zero-Expiry Auth

Authentication that never expires or needs renewal. Once issued, your passport works across all AI tools and environments permanently.