langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-21 03:45:28 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #3418] docs: add langchain-agentlair tools integration (identity, email, vault, audit trail) #2730

New Issue
Open
opened 2026-06-05 17:26:32 -04:00 by yindo · 1 comment
yindo commented 2026-06-05 17:26:32 -04:00
Owner
Copy Link
Copy Source

Originally created by @piiiico on GitHub (Apr 2, 2026).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/3418

Summary

This issue requests the addition of a documentation page for the langchain-agentlair package — an identity layer for LangChain agents.

Package details

What this integration provides

langchain-agentlair gives any LangChain agent a persistent identity — a real @agentlair.dev email address, an encrypted vault, and an immutable audit trail — in three lines of code.

Five tools included:

Tool What it does
SendEmailTool Send email from the agent's @agentlair.dev address via AWS SES
CheckInboxTool Read the agent's inbox
VaultStoreTool Store secrets/state in an encrypted cross-session vault
VaultGetTool Retrieve values from the vault
LogObservationTool Write entries to an immutable audit trail

All tools carry tool.metadata["agent_email"] — the agent's persistent identity — for downstream tracing.

Three entry points:

  • agentlair_tools(client, "mybot@agentlair.dev") — returns a list of BaseTool objects
  • AgentLairCallbackHandler — adds audit trail to any existing LangChain agent via callbacks
  • AgentLairAgent — pre-built React agent with all tools pre-wired

Why this should be added

LangChain agents are stateless by default. AgentLair solves the identity/state problem at the protocol layer:

  • Cross-session persistence: the agent's email address, vault, and audit trail survive container restarts
  • Accountable: every action logged with timestamp and agent identifier
  • Addressable: external systems can reach the agent by email

Proposed page

src/oss/python/integrations/tools/agentlair.mdx

I will submit a PR with the draft once:

  1. The package is live on PyPI
  2. This issue is approved and assigned

Notes

  • This is a tools integration (not chat model, retriever, or loader)
  • Package lives independently on PyPI — no code PR to langchain-ai repos
  • All 5 tools are BaseTool subclasses with args_schema (Pydantic v2)
  • Works with any LangChain-compatible LLM (OpenAI, Anthropic, etc.)
Originally created by @piiiico on GitHub (Apr 2, 2026). Original GitHub issue: https://github.com/langchain-ai/docs/issues/3418 ## Summary This issue requests the addition of a documentation page for the `langchain-agentlair` package — an identity layer for LangChain agents. ## Package details - **PyPI package:** [`langchain-agentlair`](https://pypi.org/project/langchain-agentlair/) *(pending publication)* - **GitHub:** https://github.com/piiiico/agentlair-langchain-integration - **Version:** 0.1.0 ## What this integration provides `langchain-agentlair` gives any LangChain agent a **persistent identity** — a real `@agentlair.dev` email address, an encrypted vault, and an immutable audit trail — in three lines of code. **Five tools included:** | Tool | What it does | |------|-------------| | `SendEmailTool` | Send email from the agent's `@agentlair.dev` address via AWS SES | | `CheckInboxTool` | Read the agent's inbox | | `VaultStoreTool` | Store secrets/state in an encrypted cross-session vault | | `VaultGetTool` | Retrieve values from the vault | | `LogObservationTool` | Write entries to an immutable audit trail | All tools carry `tool.metadata["agent_email"]` — the agent's persistent identity — for downstream tracing. **Three entry points:** - `agentlair_tools(client, "mybot@agentlair.dev")` — returns a list of `BaseTool` objects - `AgentLairCallbackHandler` — adds audit trail to any existing LangChain agent via callbacks - `AgentLairAgent` — pre-built React agent with all tools pre-wired ## Why this should be added LangChain agents are stateless by default. AgentLair solves the identity/state problem at the protocol layer: - **Cross-session persistence**: the agent's email address, vault, and audit trail survive container restarts - **Accountable**: every action logged with timestamp and agent identifier - **Addressable**: external systems can reach the agent by email ## Proposed page `src/oss/python/integrations/tools/agentlair.mdx` I will submit a PR with the draft once: 1. The package is live on PyPI 2. This issue is approved and assigned ## Notes - This is a **tools** integration (not chat model, retriever, or loader) - Package lives independently on PyPI — no code PR to langchain-ai repos - All 5 tools are `BaseTool` subclasses with `args_schema` (Pydantic v2) - Works with any LangChain-compatible LLM (OpenAI, Anthropic, etc.)
yindo added the external label 2026-06-05 17:26:32 -04:00
yindo commented 2026-06-05 17:26:32 -04:00
Author
Owner
Copy Link
Copy Source

@piiiico commented on GitHub (Apr 6, 2026):

Update (2026-04-06): Package is now live on PyPI — https://pypi.org/project/langchain-agentlair/

PR ready for review: #3419

The PR includes:

  • src/oss/python/integrations/tools/agentlair.mdx — tools integration page
  • src/oss/python/integrations/providers/agentlair.mdx — provider landing page
  • packages.yml — entry for langchain-agentlair

Also note: PR #3424 was opened by a third-party contributor covering the same scope — that one can be closed as a duplicate.

<!-- gh-comment-id:4192102130 --> @piiiico commented on GitHub (Apr 6, 2026): **Update (2026-04-06): Package is now live on PyPI** — https://pypi.org/project/langchain-agentlair/ PR ready for review: #3419 The PR includes: - `src/oss/python/integrations/tools/agentlair.mdx` — tools integration page - `src/oss/python/integrations/providers/agentlair.mdx` — provider landing page - `packages.yml` — entry for `langchain-agentlair` Also note: PR #3424 was opened by a third-party contributor covering the same scope — that one can be closed as a duplicate.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label external
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#2730
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?