zep
Zep API for long-term memory and conversation history management in AI agents. Use when user mentions "Zep", "conversation memory", "session memory", "memory search", "user facts", "agent memory", or "long-term memory".
What this skill does
## Troubleshooting
If requests fail, run `zero doctor check-connector --env-name ZEP_TOKEN` or `zero doctor check-connector --url https://api.getzep.com/api/v2/sessions --method GET`
## Authentication
All requests require an API key passed in the header:
```
Authorization: Api-Key $ZEP_TOKEN
```
> Official docs: `https://help.getzep.com/api`
## Environment Variables
| Variable | Description |
|---|---|
| `ZEP_TOKEN` | Zep API key from app.getzep.com → Settings → API Keys |
## Prerequisites
Connect the **Zep** connector at [app.vm0.ai/connectors](https://app.vm0.ai/connectors).
> **Troubleshooting:** If requests fail, run `zero doctor check-connector --env-name ZEP_TOKEN` or `zero doctor check-connector --url https://api.getzep.com/api/v2/sessions --method GET`
## Key Concepts
- **Users** — represent end users whose memory you are managing
- **Sessions** — conversation threads tied to a user; each session accumulates message history
- **Memory** — the distilled facts and context extracted from a session's messages
- **Search** — full-text and semantic search across memory and facts
Base URL: `https://api.getzep.com`
---
## Users
### Create a User
Write to `/tmp/zep_user.json`:
```json
{
"user_id": "<your-user-id>",
"email": "<user-email>",
"first_name": "<first-name>",
"last_name": "<last-name>",
"metadata": {}
}
```
```bash
curl -s -X POST "https://api.getzep.com/api/v2/users" --header "Authorization: Api-Key $ZEP_TOKEN" --header "Content-Type: application/json" -d @/tmp/zep_user.json
```
### Get a User
```bash
curl -s "https://api.getzep.com/api/v2/users/<user-id>" --header "Authorization: Api-Key $ZEP_TOKEN"
```
### List Users
```bash
curl -s "https://api.getzep.com/api/v2/users?limit=50" --header "Authorization: Api-Key $ZEP_TOKEN"
```
### Update a User
Write to `/tmp/zep_user_update.json`:
```json
{
"email": "<new-email>",
"first_name": "<new-first-name>",
"last_name": "<new-last-name>",
"metadata": {}
}
```
```bash
curl -s -X PATCH "https://api.getzep.com/api/v2/users/<user-id>" --header "Authorization: Api-Key $ZEP_TOKEN" --header "Content-Type: application/json" -d @/tmp/zep_user_update.json
```
### Delete a User
```bash
curl -s -X DELETE "https://api.getzep.com/api/v2/users/<user-id>" --header "Authorization: Api-Key $ZEP_TOKEN"
```
---
## Sessions
### Create a Session
Write to `/tmp/zep_session.json`:
```json
{
"session_id": "<your-session-id>",
"user_id": "<user-id>",
"metadata": {}
}
```
```bash
curl -s -X POST "https://api.getzep.com/api/v2/sessions" --header "Authorization: Api-Key $ZEP_TOKEN" --header "Content-Type: application/json" -d @/tmp/zep_session.json
```
### Get a Session
```bash
curl -s "https://api.getzep.com/api/v2/sessions/<session-id>" --header "Authorization: Api-Key $ZEP_TOKEN"
```
### List Sessions
```bash
curl -s "https://api.getzep.com/api/v2/sessions?limit=50" --header "Authorization: Api-Key $ZEP_TOKEN"
```
### List Sessions for a User
```bash
curl -s "https://api.getzep.com/api/v2/users/<user-id>/sessions" --header "Authorization: Api-Key $ZEP_TOKEN"
```
---
## Memory
### Add Messages to a Session
Write to `/tmp/zep_messages.json`:
```json
{
"messages": [
{
"role": "user",
"role_type": "user",
"content": "What's the weather like today?"
},
{
"role": "assistant",
"role_type": "assistant",
"content": "It's sunny and 72°F in San Francisco."
}
]
}
```
```bash
curl -s -X POST "https://api.getzep.com/api/v2/sessions/<session-id>/memory" --header "Authorization: Api-Key $ZEP_TOKEN" --header "Content-Type: application/json" -d @/tmp/zep_messages.json
```
### Get Memory for a Session
Returns the distilled memory context and recent messages for a session.
```bash
curl -s "https://api.getzep.com/api/v2/sessions/<session-id>/memory" --header "Authorization: Api-Key $ZEP_TOKEN"
```
### Delete Memory for a Session
```bash
curl -s -X DELETE "https://api.getzep.com/api/v2/sessions/<session-id>/memory" --header "Authorization: Api-Key $ZEP_TOKEN"
```
---
## Search
### Search Memory Across a User's Sessions
Write to `/tmp/zep_search.json`:
```json
{
"text": "user's preference for dark mode",
"search_scope": "facts",
"search_type": "similarity",
"limit": 10
}
```
```bash
curl -s -X POST "https://api.getzep.com/api/v2/users/<user-id>/search" --header "Authorization: Api-Key $ZEP_TOKEN" --header "Content-Type: application/json" -d @/tmp/zep_search.json
```
Key parameters:
- `text` — the query string
- `search_scope` — `"facts"` (extracted facts) or `"messages"` (raw messages)
- `search_type` — `"similarity"` (semantic) or `"mmr"` (max marginal relevance)
- `limit` — max results to return (default 10)
### Search Sessions for a User
```bash
curl -s -X POST "https://api.getzep.com/api/v2/sessions/<session-id>/search" --header "Authorization: Api-Key $ZEP_TOKEN" --header "Content-Type: application/json" -d @/tmp/zep_search.json
```
---
## Facts
### Get Facts for a User
Returns all extracted facts about a user across their sessions.
```bash
curl -s "https://api.getzep.com/api/v2/users/<user-id>/facts" --header "Authorization: Api-Key $ZEP_TOKEN"
```
---
## Common Workflows
### Persist a Conversation Turn
```bash
# 1. Ensure the user exists (create if needed)
curl -s "https://api.getzep.com/api/v2/users/<user-id>" --header "Authorization: Api-Key $ZEP_TOKEN"
# 2. Ensure the session exists (create if needed)
curl -s "https://api.getzep.com/api/v2/sessions/<session-id>" --header "Authorization: Api-Key $ZEP_TOKEN"
# 3. Add the new messages to the session
curl -s -X POST "https://api.getzep.com/api/v2/sessions/<session-id>/memory" --header "Authorization: Api-Key $ZEP_TOKEN" --header "Content-Type: application/json" -d @/tmp/zep_messages.json
```
### Load Context for a New Agent Turn
```bash
# Retrieve distilled memory + recent messages to inject into the system prompt
curl -s "https://api.getzep.com/api/v2/sessions/<session-id>/memory" --header "Authorization: Api-Key $ZEP_TOKEN"
```
---
## Guidelines
1. **Session IDs** — use stable, deterministic IDs (e.g. a conversation UUID) so the same session is reused across agent runs
2. **User IDs** — use a stable identifier (e.g. the user's account ID) rather than ephemeral values
3. **Memory context** — inject the `context` field from the memory response into the agent's system prompt to provide long-term continuity
4. **Facts vs messages** — search `facts` scope for structured user preferences; search `messages` scope for verbatim conversation recall
5. **Rate limits** — Zep enforces per-project rate limits; handle `429` responses with exponential backoff
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.