Add Cycles to Open-source projects#879
Open
amavashev wants to merge 1 commit intoe2b-dev:mainfrom
Open
Conversation
Cycles is an open-source runtime layer that enforces hard limits on AI agent spend, risk, and tool actions before they execute. The project follows the established entry format (Category, Description bullets, Links) and is inserted alphabetically between CrewAI and data-to-paper.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Adds Cycles to the Open-source projects section, inserted alphabetically between CrewAI and data-to-paper.
What is Cycles
Cycles is an open-source runtime layer (Apache 2.0) that enforces hard limits on AI agent spend, risk, and tool actions before they execute — not after. Multi-tenant by default, concurrency-safe across thousands of agents.
The reservation lifecycle (
reserve / execute / commit / release) wraps any LLM or tool call and ensures agents cannot authorize more spend or take riskier actions than policy allows. Works with OpenAI, Anthropic, MCP servers, OpenAI Agents SDK, LangChain, and CrewAI; SDKs in Python, TypeScript, Rust, and a Spring Boot starter for Java.Format
I followed the existing entry pattern exactly (
## [Name](url)+ tagline +<details>block with### Category,### Description,### Links). No image included since the repo screenshot is on the docs site rather than a stable image URL — happy to add one if you'd prefer.Why this fits the list
Thanks for maintaining this list — it's the canonical reference in the agent space.