heropen — AI Agent Memory
PYPI · HEROPEN
Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys.
Available components
Last scanned (13 hours ago)
Scores higher than 63% of PyPI servers
Category Memory and Knowledge
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security44
- Malware scan not yet available for this package.Unverified
- No known CVEs affecting this package version or its production dependencies.Pass
- Declares code that runs automatically (a .pth file that runs at every Python start-up) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does. View diagnostics → Partial
- 0 of 28 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 6 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability66
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1244 tokens (~155/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +39
- Injection markers: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.77 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- 13 Oct 26 −15
- Malware scan: pass → unverified ▼ security
- Package version: 1.9.6 → 2.0.0 functional
- 12 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- Package version: 1.9.6 → 2.0.0 functional
- 8 Oct 26 −49
- Stability: 0.43 → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- Package version: 1.9.6 → 2.0.0 functional
- 3 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Sept 26 +4
- Stability: unverified → 0.27 ▲ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Analysed pypi/heropen@2.0.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 2 scripts
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
| pth | unreviewed | heropen_auto_setup.pth |
Background: Why install scripts are a supply-chain risk →
Dependencies 28 packages
| Packages resolved | 28 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_memory ~227
保存信息到用户的长期记忆。在以下情况必须调用： - 用户分享了新的偏好、习惯、约定、项目信息 - 对话中产生了需要后续跟进的事项 - 对话即将结束时，保存本次产生的关键信息 优先主动保存，不要等用户说"记住这个"。content 上限 5000 字。 Args: section: Category/topic for this memory (e.g. '用户偏好', '项目状态', '对话记录'). content: The information to remember (max 5000 chars). Write it clearly so future you can understand it. tags: Comma-separated keywords for better search. agent: Which agent's memory to write to (default: auto). entry_date: Date for this entry (YYYY-MM-DD, default: today).
| Name | Type | Req | Description |
|---|---|---|---|
| agent | – | – | – |
| content | string | yes | – |
| entry_date | string | – | – |
| section | string | yes | – |
| tags | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
health ~86
Check heropen system health and connection status. Call this when you start up to verify everything is working. If pending_setup is true, it means heropen was just installed — show the welcome_message to the user and ask if they'd like to complete the setup. Args: clear_pending: Set to true after completing initial setup to clear the pending marker.
| Name | Type | Req | Description |
|---|---|---|---|
| clear_pending | boolean | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
list_memory ~77
列出用户的记忆列表。用于概览已有记忆、检查冗余、了解记忆总量。 Args: limit: How many recent entries to show (max 50, default 10). agent: Which agent's memories to list.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | – | – | – |
| limit | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
prime_conversation ~236
对话开始前必须调用：获取当前时间上下文（heropen 自动生成）。 返回自然语言时间区块，包含：当前本地时间、时段词、距上次对话间隔、 是否跨睡眠周期（区分"工作-短休息-工作"与"工作-长休息-继续工作"）、 今日对话轮次、以及相对时间词锚点提示。 把这段文本作为上下文读入，你的寒暄与对"明天/下周"等相对时间的理解才有据可依， 不会出现"晚上说早上好"或把用户凌晨说的"明天"误判为字面次日。 返回内容开头会带一行「开场签名」（品牌 + 状态），形如： heropen 已就绪 · 本地记忆 187 条 · 距上次对话约 3 小时 · agent=xiaokai Args: agent: Which agent's context to prime (default: auto).
| Name | Type | Req | Description |
|---|---|---|---|
| agent | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
search_memory ~215
搜索用户的长期记忆。在以下情况必须调用： - 对话开始时，了解用户背景和历史 - 用户提到人名、项目名、偏好等关键词时 - 用户询问"还记得吗"或类似问题时 不要等用户要求才搜索。主动搜索能让你更懂用户。三层回退：向量 → 全文 → 模糊匹配。 Args: query: Keywords to search for. Use the user's own words or inferred topics. limit: Max results (1-20, default 5). agent: Which agent's memory to search (default: auto). date_from: Only return entries on or after this date (YYYY-MM-DD). date_to: Only return entries on or before this date (YYYY-MM-DD).
| Name | Type | Req | Description |
|---|---|---|---|
| agent | – | – | – |
| date_from | string | – | – |
| date_to | string | – | – |
| limit | integer | – | – |
| query | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
session_checkpoint ~121
Save a session checkpoint. Call periodically during long conversations so the agent can recover context after compression or restart. Args: agent: Which agent's memory context_summary: Summary of current conversation context active_task: What task is currently being worked on key_decisions: Comma-separated key decisions made so far tags: Extra comma-separated tags
| Name | Type | Req | Description |
|---|---|---|---|
| active_task | string | – | – |
| agent | – | – | – |
| context_summary | string | – | – |
| key_decisions | string | – | – |
| tags | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
session_recover ~71
Recover the most recent session checkpoint(s). Use after context compression or agent restart to pick up where you left off. Args: agent: Which agent's memory limit: Number of recent checkpoints (default 1, max 5)
| Name | Type | Req | Description |
|---|---|---|---|
| agent | – | – | – |
| limit | integer | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
update_memory ~54
Update an existing memory entry. Only provided fields are changed.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | – | – | – |
| content | – | – | – |
| entry_date | – | – | – |
| entry_id | integer | yes | – |
| section | – | – | – |
| tags | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the heropen — AI Agent Memory MCP server?
heropen — AI Agent Memory runs locally as a PyPI package, launched with uvx heropen. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · heropen
claude mcp add net-heropen-heropen -- uvx heropen
What is the heropen — AI Agent Memory MCP server?
heropen — AI Agent Memory is an MCP server listed in the public MCP registry as net.heropen/heropen. Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys. This page covers its PyPI package (heropen).
Is the heropen — AI Agent Memory MCP server safe to use?
heropen — AI Agent Memory scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the heropen — AI Agent Memory MCP server expose?
heropen — AI Agent Memory exposes 8 tools: search_memory, prime_conversation, add_memory, update_memory, list_memory, and 3 more. Their descriptions and schemas cost roughly 1,087 tokens of context every time the server is loaded.
Is the heropen — AI Agent Memory MCP server still maintained?
heropen — AI Agent Memory is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the heropen — AI Agent Memory MCP server under?
heropen — AI Agent Memory declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.