Filter by tags:
#AI Coding
#Testing
#Software Engineering (SW)
#Database
#Security
#Bio
#MOE
#Robotics
#OCR
#TTS
#MCP
#Multimodal
#Machine Translation
#RL
#CV
#Audio
#ML
#Coding
#Image Generation
#AGI
#Agentic AI
#Infrastructure
#AI Agents
#LLMs
2026inclusionAI

LLaDA2.2-flash v2.2

Open Source
diffusion
llm

LLaDA2.2-flash is an agent-oriented Mixture-of-Experts (MoE) diffusion language model designed for long-context agentic workloads. It introduces Levenshtein Editing with DELETE and INSERT control tokens to enable efficient parallel generation, error correction, and multi-turn tool use.

128K context window with Block Routing for efficient MoE expert activation
Levenshtein Editing using DELETE and INSERT control tokens for structural sequence modification
Agentic Reinforcement Learning via L-EBPO for improved error correction
PricingOpen source under Apache License 2.0
Version2.2
2026Superlinked

SIE (Superlinked Inference Engine) v0.7.1

Open Source
Inference Engine
AI Agents

SIE is an open-source, self-hosted inference server designed to run a wide variety of AI models for agentic workflows, including embedding, reranking, entity extraction, and text generation. It provides a unified API that replaces fragmented model-specific servers, allowing developers to serve over 100 models from a single cluster with on-demand loading.

Unified OpenAI-compatible API for embeddings, chat, and completions
Multi-model GPU sharing with on-demand loading and LRU eviction
Support for 100+ models including rerankers, OCR, and entity extractors
Version0.7.1
RegionUnited States
2026Agent Orchestrator

Agent Orchestrator v0.12.1

Open Source
AI Agents
Developer Tools

Agent Orchestrator is an open-source development tool designed to manage fleets of AI coding agents in parallel. It provides a centralized dashboard to monitor agent sessions, handle git worktree isolation, and autonomously manage CI failures, code reviews, and merge conflicts.

Parallel multi-agent execution with isolated git worktrees
Autonomous CI failure recovery and review comment handling
Unified web-based dashboard for monitoring session state and PRs
Version0.12.1
RegionIndia
2026ASCII

Box v1.0

Paid
AI Agents
Cloud Sandbox

box is a persistent Linux (Ubuntu) virtual machine sandbox designed specifically for AI agents and agent factories. It provides full machine capabilities including SSH/SCP access, Docker support, and a 60fps virtual desktop, allowing agents to build, run, and ship software in isolated environments.

Persistent Ubuntu Linux VMs with SSH and SCP access
Disk-level snapshotting and fast forking for parallel agent workflows
Pre-configured environment with Docker, VS Code, Chrome, and common runtimes
Version1.0
RegionFrance
2026Mind Lab

Macaron V1 Venti vV1-Venti

Open Source
mixture-of-lora
personal-agent

Macaron-V1-Venti is a 748B-parameter flagship AI model designed for personal intelligence, complex tool use, and coding workflows. It utilizes a Mixture of LoRA (MoL) architecture built on the GLM-5.2 base model, featuring specialized adapters for chat, agentic tasks, coding, and Generative UI.

Mixture of LoRA (MoL) architecture with four specialized 1B-parameter adapters
1M token context window for long-horizon planning and complex workflows
Native support for Generative UI (GenUI) and UI4A rendering
VersionV1-Venti
RegionSingapore
2026Rei Labs

Adapt-1 vPreview

Open Source
Neuro-symbolic
Test-time learning

Adapt-1 Preview is a non-transformer, neuro-symbolic substrate designed for test-time learning. It enables applications to learn and adapt while operating by maintaining a persistent, inspectable state without requiring task-specific pretraining or an LLM in the decision loop.

Pretraining-free, non-transformer neuro-symbolic architecture
Real-time test-time learning and adaptation
Inspectable state with clear decision provenance
VersionPreview
RegionUnited States
2026Liquid AI

LFM2.5-2.6B v2.5

Open Source
edge-ai
agentic

LFM2.5-2.6B is a compact, agentic foundation model designed for efficient on-device deployment. It features a 128K context window and is specifically optimized for agentic workflows, including planning, tool use, and multi-step task execution.

128K context window for long-context workflows
Optimized for on-device agentic tasks and tool use
High-efficiency inference (220 tok/s on Apple M5 Max)
PricingFree (Open-weight)
Version2.5
2026Xata

Xata

Open Source
Postgres
Kubernetes

Xata is an open-source, cloud-native Postgres platform designed for Kubernetes that enables instant database branching using copy-on-write storage. It provides advanced features like scale-to-zero compute, high availability, and automated management, making it ideal for development environments and AI agent workloads.

Instant copy-on-write branching for TB-scale databases
Scale-to-zero compute hibernation for cost efficiency
100% vanilla Postgres compatibility with no forks
RegionUnited States
2026OpenAI

Codex Security Review vResearch Preview

Paid
Featured
AI Security
DevSecOps

Codex Security Review is an AI-powered security analysis tool designed to perform in-depth evaluations of GitHub pull requests. It analyzes code diffs, repository context, and custom threat models to identify and report security vulnerabilities with high precision.

Automated security scanning for GitHub pull requests
Context-aware analysis using repository-specific threat models
Configurable reporting thresholds for High, Critical, and Medium findings
VersionResearch Preview
RegionUnited States
2026Cursor

SDK Bridge v1.0.27

Open Source
AI Agents
Developer Tools

The Cursor SDK Bridge is an open-source protocol and local server that enables developers to drive Cursor agents from any programming language. By providing a stable sdk.v1 protobuf contract, it allows languages like Rust, Go, and Java to interact with Cursor's agent runtime without requiring direct dependency on the official TypeScript or Python SDKs.

Stable sdk.v1 protobuf contract for language-agnostic agent control
Local server architecture that embeds the official Cursor TypeScript SDK
Full support for agent lifecycle management, including creation, resumption, and streaming runs
PricingFree and Open-Source
Version1.0.27
2026Agent Plugins Technical Steering Committee (Amazon, Cursor, GitHub, Microsoft, OpenAI, Vercel)

Agent Plugins v1.0.0

Open Source
Featured
AI Agents
Interoperability

Agent Plugins is an open, vendor-neutral standard for packaging reusable components into portable plugins for AI agents. It provides a consistent format for bundling Agent Skills and Model Context Protocol (MCP) servers, allowing them to be discovered and loaded across different compatible AI agent clients.

Vendor-neutral, open-source standard for portable AI agent plugins
Unified packaging for Agent Skills and Model Context Protocol (MCP) servers
Standardized directory structure with a required plugin.json manifest
PricingFree & Open-Source
Version1.0.0
2026Amazon Web Services (AWS)

Kiro Crew v0.1.3

Open Source
AI Agents
Developer Tools

Kiro Crew is an open-source, persistent development workspace designed to transform AI coding agents into autonomous engineering teams. It enables agents to maintain context across sessions, schedule recurring tasks, and integrate with various developer tools for long-running workflows.

Persistent sessions that maintain context and memory across restarts
Autonomous task execution for long-running engineering workflows
Support for recurring jobs and scheduled maintenance tasks
PricingFree (Open Source)
Version0.1.3

🚀 Join the AI dev community — follow us everywhere

© 2026 MARKTECHPOST AI MEDIA INC. All rights reserved.Terms & ConditionsPrivacy Policy
Beta Mode