ekbasis
No liveness check has reached it yet; it is registered on GitHub and PyPI and has been in the index since 10 Oct 2026. How this is checked
Ekbasis is an open-source Python client for typed and calibrated consequence predictions. It supports one-pass predictions, chained simulations, Git guards, and integrations for AI agent workflows.
Inferred · not functionally tested
Overview
6 featuresPurpose: Helping AI agents predict and guard against the consequences of proposed actions before execution.
Inferred · not functionally tested
Audience: AI safety researchers and developers building agentic systems
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: Apache-2.0 · platforms: CLI · deployment: cli, api_only, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
ekbasis sits in PulseGate's AI security & guardrails category. Inferred · not functionally tested: It focuses on helping AI agents predict and guard against the consequences of proposed actions before execution. Inferred · not functionally tested: It is built as an open-source project for AI safety researchers and developers building agentic systems. Basis unknown · not verified: ekbasis is open source under the Apache-2.0 license. Basis unknown · not verified: It ships for the command line and API, and it can be self-hosted.
OpenInterpretability builds and maintains ekbasis, and it first shipped in 2026. Development happens publicly on GitHub with 18 stars and 36 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include consequence predictions, typed predictions, and chained simulation. 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
- Consequence predictions
- Typed predictions
- Chained simulation
- Calibration
- Git guard
- MCP integration
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit a85e9a50281d · since Oct 2026
Trust & compliance
Indexing history
2What PulseGate has recorded for this listing
Frequently asked questions about ekbasis
- What does ekbasis do?
- Inferred · not functionally tested: Ekbasis focuses on helping AI agents predict and guard against the consequences of proposed actions before execution. It is catalogued under AI security & guardrails on PulseGate.
- Who is ekbasis for?
- Inferred · not functionally tested: ekbasis is an open-source project built for AI safety researchers and developers building agentic systems.
- Does ekbasis have a free plan?
- Basis unknown · not verified: Yes — ekbasis is open source under the Apache-2.0 license and free to use.
- What platforms does ekbasis run on?
- Basis unknown · not verified: ekbasis runs on the command line and API. It can also be self-hosted.
- Is ekbasis still active?
- The GitHub repository shows 36 commits in the last 90 days.
- What projects are similar to ekbasis?
- Similar projects tracked by PulseGate include agentguard-oss, Kineti, and agent-custody.agentguard-ossKinetiagent-custody
- Who makes ekbasis?
- ekbasis is developed by OpenInterpretability.
- How long has ekbasis been around?
- ekbasis first shipped in 2026.
Also in AI security & guardrails
Same category — not a similarity match