Hippocortex Feature Catalog
A comprehensive reference of every capability in the Hippocortex platform.
0. Integration Methods
Hippocortex offers multiple integration paths, from zero-code to full manual control. All methods access the full pipeline: capture, synthesize, learn, vault, collective brain.
Gateway (Recommended)
OpenAI-compatible proxy. Change your base URL and every LLM call gets persistent memory. No SDK, no code changes. Works with any provider: OpenAI, Anthropic, Google Gemini, Groq, Together, Mistral, Fireworks, Ollama, and any OpenAI-compatible endpoint.
Reliability: ~99% with graceful fallback.
from openai import OpenAI
client = OpenAI(
base_url="https://api.hippocortex.dev/v1",
api_key="hx_live_...",
default_headers={"X-LLM-API-Key": "sk-..."},
)
See Gateway Guide for full documentation.
Auto-Instrumentation
Sentry-style monkey-patching. One import, zero config. Every OpenAI and Anthropic SDK call automatically gets memory context injection and conversation capture.
// TypeScript
import '@hippocortex/sdk/auto'
# Python
import hippocortex.auto
How it works: On import, the module patches Completions.prototype.create (OpenAI) and
Messages.prototype.create (Anthropic). Each call synthesizes relevant context, prepends it
as a system message, calls the original method, then captures the conversation. All operations
are fault-tolerant: if Hippocortex is unreachable, calls pass through unchanged.
wrap() — Transparent Client Wrapping
Wrap your OpenAI or Anthropic client instance. Explicit, typed, per-client control.
import { wrap } from '@hippocortex/sdk'
const openai = wrap(new OpenAI())
// Use exactly as before. Memory is transparent.
from hippocortex import wrap
client = wrap(OpenAI())
# Use exactly as before. Memory is transparent.
The wrapped client keeps its original type signature. Works with OpenAI and Anthropic SDKs.
OpenClaw Plugin (Recommended for OpenClaw)
The @hippocortex/hippocortex@3.2.1 plugin gives OpenClaw agents persistent memory with zero code changes. Full pipeline: capture, synthesize (semantic search, graph retrieval, collective brain, behavioral context), learn, vault, and context engine for infinite sessions.
See OpenClaw Plugin for full documentation.
Zero-Config
All integration methods support automatic configuration resolution:
- Explicit arguments
- Environment variables:
HIPPOCORTEX_API_KEY,HIPPOCORTEX_BASE_URL .hippocortex.jsonfile (searched from cwd upward to filesystem root)
1. Event Capture
Hippocortex captures agent interactions as structured events for downstream compilation and retrieval.
Supported Event Types
| # | Type | Description | Example Payload Fields |
|---|---|---|---|
| 1 | message | Conversation turns (user/assistant/system) | role, content |
| 2 | tool_call | Tool invocations with parameters | tool, args, callId |
| 3 | tool_result | Tool outputs and return values | tool, result, callId, success |
| 4 | file_edit | File modifications | path, before, after, diff |
| 5 | test_run | Test suite execution | suite, passed, failed, duration |
| 6 | command_exec | Shell command execution | command, exitCode, stdout, stderr |
| 7 | browser_action | Browser automation actions | action, url, selector, result |
| 8 | api_result | External API call results | endpoint, method, status, body |
| 9 | decision | Agent reasoning and choice points | options, chosen, reasoning |
| 10 | error | Errors and exceptions | type, message, stack, context |
| 11 | feedback | Human feedback signals | verdict, comment, rating |
| 12 | observation | Environmental observations | source, content, significance |
| 13 | outcome | Task completion and results | task, success, duration, metrics |
Batch Support
Capture up to 100 events in a single API call using POST /v1/capture/batch.
Deduplication
Events are deduplicated using idempotency keys and SHA-256 content hashing.
Salience Scoring
Every ingested event receives a salience score (0.0 to 1.0). High-salience events (errors, outcomes, decisions) are prioritized during memory compilation.
2. Context Synthesis
Retrieves compressed, relevant context for an agent's current query. The synthesis engine uses the full pipeline: semantic search, graph retrieval, collective brain, and behavioral context.
Performance
| Metric | Value |
|---|---|
| p50 latency | 18ms |
| p99 latency | 85ms |
| Max context sections | 6 |
| Default token budget | 4,000 |
| Max token budget | 32,000 |
Token Budget Management
The synthesis engine allocates tokens across reasoning sections:
| Section | Priority | Description |
|---|---|---|
procedures | Highest | Relevant task schemas and step sequences |
failures | High | Failure playbooks matching the query |
decisions | Medium | Decision policies and rules |
facts | Medium | Known facts and entity information |
causal | Lower | Causal patterns and relationships |
context | Lowest | General context and background |
Ranking Model
Context items are ranked using an 8-signal composite model:
| Signal | Weight | Description |
|---|---|---|
| Salience | 0.20 | Stored confidence/importance score |
| Recency | 0.15 | Time decay (newer items score higher) |
| Keyword Overlap | 0.15 | Query terms found in memory content |
| Entity Overlap | 0.20 | Named entities shared between query and memory |
| Graph Connectivity | 0.10 | Knowledge graph connections to query entities |
| Relation Strength | 0.05 | Direct graph relations to query subject |
| Contradiction Status | 0.10 | Active (1.0) vs deprecated (0.0) |
| Promotion Confidence | 0.05 | Original confidence assessment score |
Provenance Tracking
Every synthesis entry includes provenance references tracing back to source events.
3. Memory Compilation (Learn)
The Memory Compiler transforms raw events into structured knowledge artifacts. It operates without any LLM calls, ensuring deterministic and hallucination-free knowledge extraction.
Key Properties
| Property | Description |
|---|---|
| Zero-LLM | No language model calls. Purely algorithmic pattern extraction. |
| Deterministic | Same inputs always produce the same artifacts. |
| Incremental | Only processes events since the last compilation run. |
| Auditable | Every artifact traces back to source events. |
| Contradiction-aware | Detects and supersedes outdated knowledge. |
Compilation Modes
- Incremental: Processes only new events since the last run (default, faster)
- Full: Reprocesses all events from scratch (thorough, slower)
4. Knowledge Artifacts
The compiler produces five types of knowledge artifacts:
| Artifact Type | What It Contains |
|---|---|
| Task Schema | Learned procedures and step sequences |
| Failure Playbook | Known failure modes with recovery steps |
| Decision Policy | Conditional rules extracted from agent decisions |
| Causal Pattern | Cause-and-effect relationships between events |
| Strategy Template | High-level approaches for recurring problem types |
5. Collective Brain
Cross-session knowledge promotion. When patterns are observed across multiple sessions and agents, the collective brain promotes them to shared knowledge that benefits all agents in the account.
- Patterns are promoted based on frequency, consistency, and confidence across sessions
- Promoted knowledge is available via
synthesize()to all agents - Prevents knowledge silos between agents
- Available on Pro, Unlimited, and Team plans
6. Graph Retrieval
Knowledge graph that captures relationships between entities, tools, outcomes, and artifacts. Used during synthesis to find contextually related information that semantic search alone would miss.
- Entity extraction from captured events
- Relationship mapping between entities
- Graph traversal during context retrieval
- Enhances synthesis with connected knowledge
7. Behavioral Intelligence
Analyzes tool usage patterns and decision-making behavior across agent sessions.
- Tool usage analysis: Which tools are used most, in what sequences, with what success rates
- Decision pattern extraction: Common decision points and the choices agents make
- Session flow analysis: How agents approach different types of tasks
- Anomaly detection: Unusual patterns that may indicate problems
- Effectiveness scoring: Which approaches lead to successful outcomes
8. Encrypted Vault
Secure storage for sensitive data with AES-256-GCM envelope encryption.
Features
| Feature | Description |
|---|---|
| Envelope encryption | Two-layer encryption (DEK + KEK) |
| AES-256-GCM | Authenticated encryption with associated data |
| Permission-gated reveal | Secrets only revealed to authorized roles |
| Audit trail | Every reveal is logged with actor, timestamp, IP |
| Version history | Full version history for every vault item |
| Secret references | vault:// URI scheme for referencing without revealing |
| Auto-detection | Secrets in captured events are automatically intercepted and vaulted |
Vault API
vaultQuery()— Search vault by natural language query (metadata only)vaultReveal()— Retrieve decrypted secret value (permission-gated, audited)- Create, update, and archive vault items
- List versions for audit
9. Secret Detection
Automatically intercepts sensitive data in captured events before it enters the memory system.
- Detects secrets in event payloads during capture
- Classifies detected secrets by type and confidence level
- High-confidence secrets are automatically redirected to the vault
- Secret references (
vault://) replace raw values in stored events
Supported Secret Types
API keys (AWS, GCP, GitHub, Stripe, etc.), connection strings, tokens (JWT, OAuth, bearer), credentials, and PII.
10. Gateway
OpenAI-compatible proxy running the full pipeline. See Gateway Guide.
11. Context Engine
Powers infinite sessions for the OpenClaw plugin and other integrations. Manages context windows across long-running agent sessions by synthesizing the most relevant information within token budgets.
13. HMX Protocol
The Hippocortex Memory Exchange (HMX) Protocol is an open standard for agent memory interoperability:
- Event Schema Spec — Standardized event format across frameworks
- Artifact Schema Spec — Knowledge artifact structure and lifecycle
- Context Pack Spec — Compressed context delivery format
- Memory Fingerprint Spec — Portable compressed memory state
- Transfer Protocol Spec — Cross-agent knowledge portability
14. Memory Fingerprints
Compressed representations of an agent's memory state for portability and backup.
| Tier | Compression Ratio | Contents |
|---|---|---|
| Full | ~1:1 | All artifacts, memories, and metadata |
| Standard | ~5:1 | Active artifacts and promoted memories |
| Compact | ~20:1 | Top-confidence artifacts and key decision points |
15. Adaptive Compiler
Self-tunes compilation parameters based on telemetry feedback. Adjusts 19 parameters across five categories with safety guarantees (hard bounds, max change caps, full rollback).
16. Predictive Context
Pre-warms context packs based on predicted agent needs, reducing retrieval latency for anticipated queries.
17. Enterprise RBAC
Role-based access control with organization and team scoping. 6 organization roles, 4 team roles, 28 permissions.
18. Memory Namespaces
Scoped collections with sensitivity classification (public, internal, confidential, restricted).
19. Policy Engine
Fine-grained access control using allow/deny rules with priority evaluation.
20. Audit Logging
Comprehensive audit trail for all system operations: mutations, access, vault, authentication, administration.
21. Memory Lineage
Full provenance tracking showing how knowledge was derived from source events.
22. Lifecycle Policies
Manage retention, archival, and deletion: active → warm → cold → archived.
Feature Availability by Plan
| Feature | Free | Pro | Unlimited | Team |
|---|---|---|---|---|
| Event Capture | ✓ | ✓ | ✓ | ✓ |
| Memory Compilation | ✓ | ✓ | ✓ | ✓ |
| Context Synthesis | ✓ | ✓ | ✓ | ✓ |
| Knowledge Artifacts | ✓ | ✓ | ✓ | ✓ |
| Gateway | ✓ | ✓ | ✓ | ✓ |
| OpenClaw Plugin | ✓ | ✓ | ✓ | ✓ |
| Collective Brain | — | ✓ | ✓ | ✓ |
| Vault (Encrypted) | — | ✓ | ✓ | ✓ |
| Secret Detection | — | ✓ | ✓ | ✓ |
| Advanced Analytics | — | — | ✓ | ✓ |
| RBAC | — | — | — | ✓ |
| Memory Namespaces | — | — | — | ✓ |
| Policy Engine | — | — | — | ✓ |
| Audit Logging | — | — | — | ✓ |
| Memory Lineage | — | — | — | ✓ |
| Lifecycle Policies | — | — | — | ✓ |
| Behavioral Intelligence | — | — | — | ✓ |
| Adaptive Compiler | — | — | — | ✓ |
| Predictive Context | — | — | — | ✓ |
| Cross-Agent Transfer | — | — | — | ✓ |
| Memory Fingerprints | — | — | — | ✓ |