agent-therapy
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
agent-therapy is an MIT-licensed Python package for counselling AI agents when they are stuck, uncertain, or repeatedly failing. It supports loop recovery, reasoning conflict diagnosis, second opinions, and autonomous workflow repair for agent developers.
Inferred · not functionally tested
Overview
6 featuresPurpose: Helping stuck or repeatedly failing AI agents diagnose reasoning conflicts and recover autonomous workflows.
Inferred · not functionally tested
Audience: AI agent developers
Inferred · not functionally tested
Functions: agents, workflow_automation
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · 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.
agent-therapy sits in PulseGate's Frameworks & runtimes category. Inferred · not functionally tested: It focuses on helping stuck or repeatedly failing AI agents diagnose reasoning conflicts and recover autonomous workflows. Inferred · not functionally tested: agent-therapy is an open-source project aimed at AI agent developers. Basis unknown · not verified: agent-therapy is open source under the MIT license. Basis unknown · not verified: It runs on the command line and API, and it can be self-hosted.
Behind agent-therapy is bencium, and it first shipped in 2026. The project is developed in the open on GitHub with 15 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include loop detection, agent counselling, and conflict diagnosis. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Loop detection
- Agent counselling
- Conflict diagnosis
- Loop recovery
- Workflow repair
- Second opinions
Topics: Inferred · not functionally tested
Built with & integrations
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed11 Oct · 12:25 UTCagent-therapy seen via PyPI Bulk EnumeratorSource: PyPI Bulk Enumerator · Open
Frequently asked questions about agent-therapy
- What does agent-therapy do?
- Inferred · not functionally tested: Agent-therapy focuses on helping stuck or repeatedly failing AI agents diagnose reasoning conflicts and recover autonomous workflows. It is catalogued under Frameworks & runtimes on PulseGate.
- Who should use agent-therapy?
- Inferred · not functionally tested: agent-therapy is an open-source project built for AI agent developers.
- Is agent-therapy free?
- Basis unknown · not verified: Yes — agent-therapy is open source under the MIT license and free to use.
- What platforms does agent-therapy run on?
- Basis unknown · not verified: agent-therapy runs on the command line and API. It can also be self-hosted.
- Is agent-therapy still maintained?
- The GitHub repository shows 15 commits in the last 90 days.
- What are alternatives to agent-therapy?
- Similar projects tracked by PulseGate include Therapeutical AI, Agentification Agency, and agentidem.Therapeutical AIAgentification Agencyagentidem
- Who develops agent-therapy?
- agent-therapy is developed by bencium.
- When did agent-therapy launch?
- agent-therapy first shipped in 2026.
Similar projects
Closest matches by what these projects do