· 2 observations
Technical updates · 2
Package or technical metadata updated
View technical comparison →Package or technical metadata updated
View technical comparison →Synnada v0.2.4
Build specialist agents.
From the developer
Listing not observed in the last 24 hours. Check collection status.
Not specified in the available declarations: limitations, pricing & account requirements.
Design a Python tool that tests code changes against a benchmark.
Developer declarations; not independently tested. Listing last checked Oct 10, 2026. Package observed Oct 10, 2026.
From the marketplace listing
Your coding agent uses Recurse to define Python tools and checks around a task. An LLM calls those tools to explore alternatives and refine results. Execution is serverless: expose the workload as an MCP server for use in agentic workflows, or run it to completion. Requires the Recurse SDK and a Recurse account.
Language: English · Automatically detected from descriptions.
· 2 observations
Package or technical metadata updated
View technical comparison →Package or technical metadata updated
View technical comparison →Finding similar plugins… Results will appear here automatically.
Browse plugins →--- name: recurse description: Build and run custom agents with Recurse for tasks that benefit from test-time compute and iterative refinement. Examples include design exploration, performance optimization, and generating artifacts that improve through verification and revision. Use this skill when designing an adaptive component that solves a specific problem. When necessary, clarify uncertain requirements on the goal and constraints. --- # Recurse Recurse hosts custom agents that work with Python tools. You shape the task, tools, and verifiers to define custom agents, they iterate on candidate results without you supervising their every step. You author the agents locally; `recurse run` executes them on a serverless runtime. Deploying a custom agent as an MCP makes it available for ongoing future use. ## When to choose Recurse Recurse is especially useful when: - The task is amenable to iterative approaches where feedback can guide successive refinement of a candidate result, or exploration of other candidates. - There are many such approaches to try. This involves a substantial search over a design space: try variants, tune performance, refine artifact quality. The aim is to discover progressively better approaches (e.g. tools, prompts, verifiers) to improve the objective while meeting constraints. The best achievable result need not be known. For example: - **Design a lighter mounting bracket.** Given a CAD model, material, and load cases, find a lighter manufacturable design that satisfies strength and stiffness limits. A general-purpose harness can make an edit and run a simulation, but a thorough exploration requires many competing attempts. A Recurse agent varies geometry, uses numerical stress and displacement checks, and preserves the lightest feasible candidate. - **Generate diverse puzzle levels.** Produce levels matching a concept, mechanic mix, difficulty, and play time while avoiding similarity to a growing corpus. This is a multidimensional search requiring substantial trial and error; general-purpose harnesses tend to follow a generic workflow and drift from the search objectives. A Recurse agent explores variants using solvability verifiers and numerical measures of mechanic usage, solution length, difficulty, and corpus similarity. - **Generate 3D objects at scale.** A general-purpose harness can create a one-off 3-D model of a bag or a shoe from a picture, but handcrafting the last object-specific details makes scaling impractical. Many objects share common construction and rendering operations, but details like straps, pockets, soles, and laces require special tools. Recurse agents iterate through tool combinations and compare renders. When missing capabilities block progress, you arm the agents with new tools, expanding what future incarnations can produce. ## The Recurse harness A Recurse agent calls an LLM in a special, serverless harness whose FSM structure guides the LLM to iteratively solve problems via Python tools. You focus on defining the prompt, tools, and verifiers for your custom agent, create an `agent.yaml` manifest file to inventory them, and use the Recurse SDK to bundle them for execution in the harness. The harness executes the LLM's tool calls, retains their results, and presents measurements/errors to the LLM for reasoning and decision-making. This lets it explore alternatives and refine results across iterations. The LLM may request several tool calls at the same time, and chain one tool's result into another. The harness automatically resolves such dependencies: calls wait for the values they require, while independent calls can run simultaneously for fast execution. Not all tool composition has to take place over a single iteration: the harness provides a way for the LLM to store tool return values in program memory as Python objects, collect results over multiple rounds, and compose them together when it has all the values it needs. In such cases,
Preview of the first 4,000 characters. Read full instructions →
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
Package observed Oct 10, 2026.
plugins_6aa9e5854d588191a0a6bf357da86329
Download plugin data (JSON)Plugin details: served from cache. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.