Skip to main content
Public BetaWe're in Public Beta. Things may break. Please report issues via the Support tab.

One Memory
Every AI

10 memory types for codebases, knowledge graph for context discovery, sub-10ms semantic search

Claude CodeCursorGitHub CopilotWindsurfCodex CLIGemini CLI
Claude CodeCursorGitHub CopilotWindsurfCodex CLIGemini CLI
Claude CodeCursorGitHub CopilotWindsurfCodex CLIGemini CLI
Claude CodeCursorGitHub CopilotWindsurfCodex CLIGemini CLI
Codebase Memory

9 Memory Types for Your Codebase

Structured memory your AI coding assistant understands and uses automatically

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. 12 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

Connected Codebase Memory

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

Relationship Types
implementsreferencessupersedesrelates_tocaused_byresolvesdocumented_independs_onblocksduplicatesvalidatesreproduces
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

29 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

Context Builder

Bootstrap AI context from requirements

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
Context Builder

Bootstrap Your AI's Context

Describe your architecture. AI creates structured memory with relationships - your coding assistant now has full context.

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.

Powered by:
GPT-4ClaudeGemini
REST API

Works With Any AI Tool

210+ endpoints for tools without MCP support. Full 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

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
Background Agents

Self-Maintaining Memory

5 autonomous agents run in the background to keep your memory store healthy, optimized, and current. Like Redis has BGSAVE - ACE has intelligent maintenance.

Memory Cleanup

Detects duplicate memories (>0.95 cosine similarity), archives stale entries, and reports storage metrics per namespace.

Observation Consolidator

Merges related observations into consolidated insights. Multiple similar detections become a single high-confidence finding.

Issue Triage

Auto-assigns severity using AI, links related issues, suggests solutions from resolved history, and flags stale issues.

Graph Maintenance

Cleans up broken links, removes duplicate relationships, reports graph connectivity stats and orphaned nodes.

Context Optimizer

Scores memory relevance, refreshes stale embeddings, and optimizes context retrieval for token efficiency.

Temporal Knowledge Graph

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

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
  • Graph distance reranking for context-aware results
  • Configurable weights for your use case
Python SDK

ace3-memory on PyPI

Full Python SDK with async support, Pydantic models, and resource classes for all entity types.

from ace3 import ACEClient

ace = ACEClient(
  url="http://localhost:7777",
  api_key="ace_sk_..."
)

# Remember something
ace.remember("auth", {"method": "JWT"})

# Search with semantic understanding
results = ace.recall("authentication")

# Track an issue
ace.issues.create(
  title="Login race condition",
  severity="high"
)