librarian-a2a
No liveness check has reached it yet; it is registered on GitHub and PyPI and has been in the index since 11 Oct 2026. How this is checked
Librarian A2A is an open-source agent that learns APIs on demand from their specifications and exposes controlled access to other agents. It supports policy-limited reads, audited actions, and human approval for writes, targeting developers building agentic systems.
Inferred · not functionally tested
Overview
6 featuresPurpose: Giving AI agents safe, policy-controlled access to unfamiliar APIs without allowing unapproved writes.
Inferred · not functionally tested
Audience: developers building AI agents and API integrations
Inferred · not functionally tested
Functions: agents, data_extraction
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
In the Frameworks & runtimes space, librarian-a2a takes a focused approach. Inferred · not functionally tested: It focuses on giving AI agents safe, policy-controlled access to unfamiliar APIs without allowing unapproved writes. Inferred · not functionally tested: librarian-a2a is an open-source project aimed at developers building AI agents and API integrations. Basis unknown · not verified: librarian-a2a is open source under the Apache-2.0 license. Basis unknown · not verified: librarian-a2a is available on the command line and API, and it can be self-hosted.
It is developed by Kultar, and it first shipped in 2026. Development happens publicly on GitHub with 44 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are API learning, openAPI support, and policy controls. Inferred · not functionally tested: Catalogued interfaces include a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- API learning
- OpenAPI support
- Policy controls
- Audited access
- Human approvals
- Read restrictions
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit 4ecd96d37fed · since Oct 2026
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed11 Oct · 21:15 UTClibrarian-a2a seen via PyPI Bulk EnumeratorSource: PyPI Bulk Enumerator · Open
Frequently asked questions about librarian-a2a
- What is librarian-a2a?
- Inferred · not functionally tested: Librarian-a2a focuses on giving AI agents safe, policy-controlled access to unfamiliar APIs without allowing unapproved writes. It is catalogued under Frameworks & runtimes on PulseGate.
- Who is librarian-a2a for?
- Inferred · not functionally tested: librarian-a2a is an open-source project built for developers building AI agents and API integrations.
- Is librarian-a2a free?
- Basis unknown · not verified: Yes — librarian-a2a is open source under the Apache-2.0 license and free to use.
- What platforms does librarian-a2a run on?
- Basis unknown · not verified: librarian-a2a runs on the command line and API. It can also be self-hosted.
- Is librarian-a2a still active?
- The GitHub repository shows 44 commits in the last 90 days.
- What are alternatives to librarian-a2a?
- Similar projects tracked by PulseGate include iris-harness, Auto Research, and threads-mcp.iris-harnessAuto Researchthreads-mcp
- Who makes librarian-a2a?
- librarian-a2a is developed by Kultar.
- When did librarian-a2a launch?
- librarian-a2a first shipped in 2026.
Also in Frameworks & runtimes
Same category — not a similarity match