Add Semantic Chunking as a chunking option in Lamatic. It's available in LangChain's experimental module via SemanticChunker and splits text based on meaning rather than fixed character/token counts — making it much better for RAG use cases where chunk quality directly impacts retrieval accuracy. Worth testing as an optional chunking strategy alongside the existing splitters.

Akshat Virmani 23 days ago

👏🏻 Feedback

Problem: After an incident, multiple flows may fail due to the same underlying issue. Currently, we have to retry each failed flow individually from Studio, which is time-consuming and inefficient when there are a large number of failures. Request: Add a Bulk Retry functionality in Studio that allows users to select multiple failed flow executions and retry them together in a single action. Expected Benefit: This would significantly reduce manual effort and make incident recovery faster, especially when a large number of flows are affected by the same incident.

Lima about 12 hours ago

💡 Feature Requests

One of our customers is currently using our Enterprise API to manage their workflows programmatically, including creating workflows, triggering executions, and performing other workflow-related actions through the API. However, there is currently a limitation with the Enterprise API: there is no functionality available to execute a workflow directly inside a container through a triggering API request. While customers can trigger and manage workflows using the existing API, they cannot specify or initiate the execution of a workflow within a containerized environment through the API. https://lamatic.notion.site/Lamatic-Enterprise-API-1a02e0e26128801ba14cc8184926b78d

Lima about 13 hours ago

💡 Feature Requests

Create knowledge stacks that connect PDFs, websites, drives, and other sources into reusable data sets. Types of Knowledge Stacks integration Upload PDF Connect Google Drive / Data Integrations Connect Website

Aman Sharma 29 days ago

👏🏻 Feedback

Improve the UI of the Reports Page along with adding the following information about there Project in a meaningful manner Request Total Requests - over time By Flow By Error Code Execution Durations - over time By Flow Model - Costs & Token - Total / By model Costs - over time By Flow By model Tokens By Flow By model Latency By Flow Model

Aman Sharma about 1 month ago

👏🏻 Feedback

Rollback Tool Suite for Dev MCP

Pat Carney 2 months ago

1

MCP

💡 Feature Requests

Feature - When nodes are added or removed in the flow UI, the layout automatically re-formats. Why - This causes unexpected changes in the flow's appearance, leading to a frustrating user experience. Where would it help most - This feature gives users control over the flow formatting behavior, improving usability and reducing frustration. Extras - Introduce a toggle switch that allows users to choose whether they want auto-formatting enabled or disabled. Auto-format ON: The flow automatically adjusts layout when nodes change. Auto-format OFF: The flow layout remains unchanged, preserving the user’s manual arrangement even when nodes are added or removed. Sample format Image before adding END Node Format image after adding END Node

Nilesh Patil 5 months ago

Low Priority

+1

💡 Feature Requests

Multi-tab Support and Flow Comparison Enable right-click to open flows in new tabs for easy comparison Support multiple tabs within the main window (similar to how Linear handles native apps) Display full flow names - currently get cut off/truncated in the UI, making it difficult to distinguish between flows Allow side-by-side visual comparison of different flow versions Consider implementing an Electron wrapper for native app experience with better tab support Cross-Environment Flow Navigation Ability to change environments within a single flow view - users want to see what the same flow looks like in staging while viewing production Maintain flow state when switching environments instead of returning to flow home screen Use flow slug associations to link flows across environments (dev/staging/production) Reduce manual effort required to promote workflows from dev → staging → production

Aman Sharma 6 months ago

💡 Feature Requests

There should be option to add zod schema as a variable in generate json node

Ramandeep Singh 6 months ago

💡 Feature Requests

Global variables panel separate from flow editor for non-developer operators Locked flow state where operators can edit variables without accessing full flow editor Highlight node associations when editing variables to show which nodes they belong to Overview/home tab combining reports and high-level flow statistics Unlock button system for accessing advanced editing features

Aman Sharma 6 months ago

UI/UX

💡 Feature Requests

An open-source SDK to address developer adoption barriers and vendor lock-in concerns that are currently limiting growth. Problem Developers resist Lamatic's no-code/low-code platform due to limited library support, lack of local development capabilities, missing CLI tools, and weak version control integration Enterprise and startup customers worry about vendor lock-in and business continuity if Lamatic changes pricing or discontinues service Competitors offering open-source alternatives have an advantage Proposed Solution Build a standalone, open-source SDK enabling developers to: Develop AI agents/systems locally in their preferred IDE Test and debug offline without cloud dependency Use Git for version control across all project components Create custom integrations and capabilities Deploy anywhere (on-premise, private/public cloud, or Lamatic-managed) Compile flows into executable code via CI/CD pipelines Core Architecture YAML-based configuration system with: Pre-built node libraries for AI components Containerized runtime (Pod + Core) executing configurations Compiler for optimizing YAML into executable workers Local web editor accessible via localhost CLI for all development operations Multiple invocation methods (API, webhooks, widgets)

Aman Sharma 7 months ago

💡 Feature Requests

The nodes are embedded inline with formatting artifacts (hello\\nhello), apparent test content, and no versioning metadata. Editing it requires understanding the entire config file, and changes produce noisy diffs that obscure actual prompt improvements. Before: prompts: - id: 187c2f4b-c23d-4545-abef-73dc897d6b7b role: assistant content: >- hello hello Important:please provide the response in wrap text format... After: prompts: - id: rag_system_prompt_v1 role: assistant # Edit prompts in /prompts/rag_system.md — supports preview & versioning contentRef: ./prompts/rag_system.md version: "1.2.0" lastUpdated: "2025-01-15" Developer Impact: Prompts become first-class artifacts — reviewable in PRs, A/B testable, and editable without touching pipeline config.

Aman Sharma 7 months ago

💡 Feature Requests

Provide integration to external graphDB like Neo4J

Aman Sharma 7 months ago

🔌 Integration

Maximum zoom in level controls - prevent excessive zooming that makes interface unusable Maintain consistent zoom levels with horizontal scroll when flows extend beyond screen width Reset zoom level functionality with percentage display Boundary controls for zoom out levels to maintain readability

Aman Sharma 6 months ago

💡 Feature Requests

When there is logic on a node and it is like retry or any logic, I think the node should have an indicator that there is logic applied. Whether that's the little retry logo, the little blue square, whatever it might be, because when you've got forty nodes on a canvas and maybe ten of those are LLM nodes that you want to put retry logic on, you can't retain the knowledge and understanding if you put it to all of them. You have to keep checking them all over again. It would be great if I could see exactly which ones I've already applied the logic to.

Aman Sharma 7 months ago

💡 Feature Requests

Ability to Create Prompt Snipped Library Which could be synced across various AI nodes

Aman Sharma 7 months ago

💡 Feature Requests

Ability to college following user meta [ UserID, SessionID, OrgID ] in API request and pass it to - Logs - Reports - External telemetry - Langfuse

Aman Sharma 7 months ago

💡 Feature Requests

Give option to pass custom input to a node on Testing to individually pass a particular test case instead of executing the whole flow

Vamsi Yechoor 7 months ago

💡 Feature Requests

Show Testing Meta Data should show some more details • show timings and latency • Parallel execution doesn't show accurate timings instead mimic the timings from a sequential execution

Vamsi Yechoor 7 months ago

💡 Feature Requests

Support for Cognee Integration in Agentic Flow memory support

Vrijraj Singh 7 months ago

👏🏻 Feedback