Why it matters
This tool provides a shared workspace for coding agents, allowing them to build upon each other's work and avoid redundant efforts. Developers can leverage this for more efficient team-based AI development and complex task execution.

What changed

OpenCrawl Core has been released as a multiplayer context layer for coding agents, aiming to facilitate collaboration and shared understanding within AI development teams. The system allows agents to access and contribute to a shared knowledge base, including captured sessions, memory files, and connected external sources. This enables agents to find previously generated code, commands, and results, preventing duplication of effort and accelerating development cycles. Key features include a shared search capability, a message board for updates and subscriptions, and agent mentions for direct communication. OpenCrawl Core supports integration with models like Claude Code and Codex, and is extensible to other Multi-Agent Coordination Protocol (MCP) clients for searching.

Deployment and Access

OpenCrawl Core offers flexible deployment options. Developers can start a local development preview by cloning the repository and running a setup script (./dev/up --no-airbyte). This provides access to a web console at http://localhost:8092 after initial setup. For more robust deployments, Kubernetes support is available through a Helm self-host kit, utilizing published images. Single Docker host deployments are also documented. For users preferring a managed solution, OpenCrawl Cloud is available.

Release Channels and Stability

The project maintains different release channels. The main branch serves as an unstable development channel. Stable releases are provided through versioned helm-v* self-host kits, which are generated weekly from validated commits on main. Users can select specific tagged kits from the Releases section for fixed source versions and image digests. The Cloud offering consumes development builds independently.

Data Capture and Privacy

Data capture within OpenCrawl Core is opt-in. However, sessions and memories are team-visible by default, which may include sensitive information. The project advises users to review privacy policies and exclusion settings before enabling capture to manage data visibility appropriately.

Agent Search Functionality

For agent search, the opencrawl_search_v1 tool is recommended, followed by opencrawl_search and then the generic search tool. Newer server versions may omit tool output and the current chat by default, requiring explicit opt-in via includeToolOutputs and includeCurrentSession parameters. Developers should check the searchContext in the response to confirm whether exclusions are active, especially when interacting with older server instances.

Why it matters for builders

OpenCrawl Core addresses a critical need for better coordination and knowledge sharing among AI coding agents. By providing a shared context layer, it allows multiple agents to work cohesively on complex projects, significantly boosting productivity and reducing the likelihood of agents working in silos or repeating tasks. This is particularly valuable for teams developing sophisticated AI applications or managing large codebases.

Practical impact

Developers can begin experimenting with OpenCrawl Core by cloning the repository and setting up a local development environment. This allows for immediate testing of its collaborative features with compatible AI models. For production use, exploring the Helm charts for Kubernetes or the Docker deployment options is recommended. Teams should carefully consider the privacy implications of shared memory and sessions and configure exclusions as needed.

Caveats and source limits

The provided source indicates that the project is in a "Pre-1.0 preview" state, suggesting potential for breaking changes and evolving features. Specific performance benchmarks or detailed comparisons against other agent coordination tools are not present in the source material. Pricing for the OpenCrawl Cloud managed service is also not detailed.

Sources

Written with AI assistance from the linked sources; every claim below was checked against them automatically. How we produce articles.

Claim check: 8/8 supported claims - 8 evidence links - 100% avg confidence
  • OpenCrawl Core provides a multiplayer context layer for coding agents.supported - github.com
  • OpenCrawl Core enables agents to share search results, memory files, and coordinate actions.supported - github.com
  • The system works with Claude Code and Codex, and supports other MCP clients for searching.supported - github.com
  • OpenCrawl Core can be self-hosted via Docker or Kubernetes using Helm charts.supported - github.com
  • A managed workspace, OpenCrawl Cloud, is available.supported - github.com
  • The project is licensed under Apache-2.0, with plugins under MIT.supported - github.com
  • OpenCrawl Core is written in TypeScript.supported - github.com
  • The latest release is cli-v0.4.118.supported - github.com

Caveats

  • The source describes this as a 'fresh release' and 'Pre-1.0 preview'.
  • Single-source caution: verify critical details at the linked source.
Radar score 87/100 - how it was calculated
Reliability82
Freshness100
Novelty77
Technical85
Developer96
Ecosystem72
Confidence96
  • Reliability 82: GitHub metadata supports source trust
  • Freshness 100: Fresh GitHub release date
  • Novelty 77: Fresh GitHub release
  • Technical 85: Repository technical metadata
  • Developer 96: Developer tooling signals
  • Ecosystem 72: Fresh GitHub release
  • Confidence 96: Claims have reliable evidence
Share
XLinkedInHacker News

Discussion

Loading comments...

Related articles

Agents - Nov 16, 2026Myco: Agent Hub for Cross-Machine CoordinationMyco is a self-hosted agent orchestration tool designed to connect AI agents like Claude Code and Codex across different machines. It facilitates agent discovery, task delegation, and communication through a central hub, all packaged as a single Go binary with a one-line setup.Agents - Nov 18, 2026llmscribe v1.4.1: AI Agent Filesystem Interfacellmscribe has released version 1.4.1, offering a structured interface for AI agents to interact with local project files across Linux, macOS, and Windows. This Python-based tool aims to provide a consistent filesystem layer for AI agents.Agents - Nov 17, 2026BuilderIO Agent Native: Framework for Agentic AppsBuilderIO Agent Native is an open-source TypeScript framework designed for building agentic applications. It recently released version v0.1.298, indicating active development and a focus on providing tools for AI agents.Agents - Nov 16, 2026Node9 Proxy Adds Access Control for AI AgentsNode9 Proxy has released version 2.61.1, introducing enhanced access control for AI agents. This tool allows developers to define permissions for agents interacting with tools like Claude Code, Codex, and Gemini, and provides auditing capabilities.Agents - Nov 20, 2026SiYuan v3.8.11-rc.3: Knowledge Workspace with AI Agent IntegrationSiYuan has released version v3.8.11-rc.3 of its open-source, privacy-first knowledge workspace. This update enhances the platform's capabilities for human-AI agent collaboration, building on its existing features for personal knowledge management.Agents - Nov 19, 2026jnMetaCode/agency-agents-zh: 277 AI Experts & OrchestratorThe jnMetaCode/agency-agents-zh repository offers 277 plug-and-play AI expert roles, supporting over 20 tools like Claude Code, Cursor, and Copilot. It includes 64 original agents tailored for the Chinese market across various sectors, and integrates with the agency-orchestrator for DAG-based multi-agent collaboration.