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
10 Structured Entity Types
Typed, structured memory your AI agents understand and use automatically — not unstructured key-value blobs
Debug context that persists. Stack traces, root causes, solutions. Your AI won't hit the same bug twice.
Why you chose React over Vue. Why PostgreSQL over MongoDB. Your AI follows the rationale, not just the choice.
Pick up where you left off. Your AI knows what you were working on, even after closing the terminal.
Your AI understands your stack. Components, technologies, dependencies - all mapped and connected.
Rules your AI applies automatically. Team conventions, linting preferences, naming patterns.
Reusable solutions your AI remembers. 'We solved this before' - and your AI knows exactly how.
Cross-memory labels for organization. Your AI uses tags to find related context across all memory types.
Knowledge graph links your AI traverses. 15 relationship types help discover connected context.
Flexible storage for anything else. Context that doesn't fit other types but matters to your project.
Connected Codebase Memory
15 relationship types let your AI traverse connections. Error → root cause → fix → prevention.
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
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
Error History
Debug context that persists
ADRs & Patterns
Capture decisions and code patterns
Graph
Navigate relationships
Search
Deep semantic search
Session
Session context that persists
Plans
Requirements to structured memory in one call
Observer
Proactive error detection and learning
Agents
Background memory maintenance
Namespaces
Multi-project workspace management
Also Includes
- 9 read-only resources
- 6 workflow prompts
- Full MCP compliance
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.
Enter your requirements in natural language. Add context about your tech stack and constraints.
AI creates ADRs, architecture, code patterns, coding standards - all linked with relationships.
Review the context, then save to memory. Your AI coding assistant now has full project context.
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.
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"}}'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"}'Sub-10ms Context Retrieval
True semantic understanding. Your AI finds relevant context even when wording differs. No latency added to your workflow.
Search across all memory types at once - errors, ADRs, code patterns, architecture.
"Find similar bugs" actually works. Your AI finds past fixes and applies them automatically.
Your AI gets comprehensive context combining ADRs, coding standards, and architecture for any question.
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.
Organize by project, team, or purpose. Complete isolation between namespaces.
Owner, Admin, Write, Read permissions. Invite by email. Manage from dashboard.
Everyone's AI sees the same context. One developer fixes a bug, everyone's AI learns the solution.
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.
Automatically scan AI-generated code for errors, anti-patterns, and violations of your coding standards.
Check new code against existing architecture decisions and patterns. Detect contradictions before they cause bugs.
Get feedback from different perspectives - developer, architect, QA, or security. Each role focuses on relevant concerns.
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 patterns10 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.
Validates and repairs knowledge graph relationships. Fixes broken links, removes duplicates, and reports connectivity stats.
Validates input quality before storage. Checks completeness, consistency, and ensures new data meets your standards.
Identifies near-duplicate memories and merges them while preserving unique information across all entity types.
Catches contradictions between memories, ADRs, and patterns. Uses LLM reasoning to detect semantic conflicts humans miss.
Discovers missing links between entities. Suggests connections your AI should know about based on content analysis.
Surfaces patterns and risks across your memory store. Detects architectural drift, recurring errors, and emerging trends.
Detects recurring patterns in work logs, decisions, and issues. Surfaces actionable insights from your project history.
Extracts patterns from Observer findings. Automatically creates searchable memories from recurring observations.
Tracks session state and ensures smooth context continuity across conversations. Maintains session history.
Records decisions with rationale and tracks outcomes for accountability. Ensures important choices are captured.
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.
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.
"What did we know on January 15th?" - traverse the graph as it existed at any point in time with the as_of parameter.
Every relationship change is versioned. See the full history of how connections between entities evolved over time.
Group related entities into temporal episodes - work sessions, deployments, code reviews. Track what happened together.
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
Semantic + Graph Intelligence
Combines semantic similarity (0.6 weight) with graph proximity (0.4 weight) for results that understand both meaning and relationships.
Embeddings on all 10 entity types. Every memory, decision, issue, and pattern is semantically searchable.
Graph distance reranking for context-aware results. Related entities are boosted based on knowledge graph proximity.
Tune the balance between semantic similarity and graph proximity for your specific use case.
The Evolution Layer
Other platforms store memories. ACE3 evolves cognition. Eight behavioral traits that adapt through every interaction.
Perception, Reasoning, Empathy, Memory, Expression, Adaptation, Regulation, Integration — each evolves independently.
Fork agents with domain-specific behavioral biases. Security reviewers, compliance auditors, creative assistants.
See how your AI's behavior evolved over time. Every generation, mutation, and adaptation is recorded.
Traits activate and mutate in real-time as your AI processes information. Watch your AI develop a unique behavioral signature.
Portable AI Identity
Device-bound cryptographic authentication that never expires. Passport stamps track achievements, trust scores grow over time.
Device-bound keys that uniquely identify your AI agent. No passwords, no tokens to rotate. Hardware-level security.
Passport stamps record achievements and usage milestones. Trust scores grow organically as your AI proves reliable over time.
Authentication that never expires or needs renewal. Once issued, your passport works across all AI tools and environments permanently.