Skip to main content

Up Next

  • Enhanced multi-stage pipeline optimization
  • Expanded model provider support
  • Improved developer experience tools
  • More production-ready examples and cookbooks

Changelog

2025-12-05
synth-large for Research Agents & MIPRO/GEPA Visualizations
  • synth-large model now available in Research Agent harness for MIPRO optimization
  • Improved MIPRO and GEPA visualizations in the dashboard
Read full breakdown →
2025-11-28
Research Agents & Language-Agnostic Optimization
  • Research Agents: Automated prompt optimization in sandboxed environments
  • Language-Agnostic: OpenAPI contracts enable Task Apps in any language
  • Multi-interface access: Web Dashboard, Python SDK, and CLI for Research Agents
  • Complete polyglot examples in Rust, Go, TypeScript, and Zig
Read full breakdown →
2025-11-21
In-Process Task Apps, Gemini 3 & Production Examples
  • In-Process Task Apps: Complete MIPRO and GEPA optimization with automatic task app and tunnel management
  • Gemini 3 Model Support: Google’s latest Gemini 3 models now supported
  • Production-Ready Examples: Complete pipeline examples for GEPA and MIPRO
  • SDK Release 0.2.25.dev1: Latest package updates
Read full breakdown →
2025-11-14
Artifacts CLI, Experiment Queue & Session Pricing
  • Artifacts CLI: Unified command suite for managing all Synth AI artifacts
  • Experiment Queue System: Redis-based queue with Celery workers
  • Session-Based Pricing: Comprehensive usage tracking and budget enforcement
  • Cloudflare Tunnel Support: Quick tunnels and managed tunnels for task app deployment
  • Task App Discovery: Multi-method discovery and health checking via synth-ai scan
  • First-Class Codex Support: Synth models now work seamlessly with Codex CLI workflows
Read full breakdown →
2025-11-07
Multi-Stage Optimizers & GEPA Algorithm
  • Multi-stage pipeline optimization for both MIPRO and GEPA algorithms
  • GEPA Algorithm: Genetic Evolution for Prompt Optimization now available
  • Google Gemini model support (gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite)
  • Expanded OpenAI model support (GPT-4o, GPT-4.1, GPT-5 families)
  • Prompt ID-based URLs for better traceability and concurrency
Read full breakdown →
2025-10-31
Terminal Training Logs & Qwen-VL RL
  • Full terminal streaming logs for both SFT and RL training
  • Hosted Synth judges with per-job overrides and rubric selection
  • Rubric-aware filtering for SFT pipelines
  • Qwen-VL support across SFT & RL with built-in vision collators
  • Real-time status updates, detailed event logs, and full metrics logging
Read full breakdown →
2025-10-17
Qwen Coder, Turso & H200 Topologies
  • Qwen Coder models supported across SFT and inference workflows
  • SDK migrated to Turso for concurrency and higher throughput
  • More training topologies on H200s with additional tensor/pipeline/data parallel layouts
  • Full LoRA support for Policy Gradient and pipelined RL async rollouts
Read full breakdown →
2025-10-10
LoRA, MoE & Large Model Support
  • Expanded Qwen catalog with SFT and inference presets for all Qwen releases
  • Large-model inference & training topologies (2×, 4×, 8× layouts)
  • LoRA-first SFT as first-class training mode across all Qwen topologies
  • Turnkey rollout with automatic SKU surfacing
Read full breakdown →
2025-09-26
Platform Updates
  • Enhanced rollout viewer with real-time metrics and progress tracking
  • B200 & H200 GPU support for training and inference workloads
  • Faster inference with optimized pipeline and improved throughput
  • GSPO (Group Sequence Policy Optimization) algorithm integration
Read full breakdown →
2025-09-19
Online RL (customer-visible features)
  • Organization-scoped environment credentials with sealed-box encryption
  • First-party Task App integration with authenticated rollouts
  • Single-node, multi-GPU Online RL with configurable tensor parallelism
  • Production run flow with monitoring and checkpoint inference
Read full breakdown →
2025-08-08
SDK Releases 0.2.2.dev1 & 0.2.2.dev2
  • Fine-tuning (SFT) endpoints available and documented end-to-end
  • Interactive demo launcher (uvx synth-ai demo) with finetuning flow for Qwen 4B
  • Live polling output during training with real-time status updates
  • New backend balance APIs and CLI for account visibility
  • CLI utilities: balance, traces, and man commands
Read full breakdown →
2025-08-01
SDK Releases 0.2.1.dev1 & 0.2.2.dev0
  • Environment Registration API for custom environments
  • Turso/sqld daemon support with local-first replicas
  • Environment Service Daemon via uvx synth-ai serve
  • Initial development release
Read full breakdown →
2025-02-03
Cuvier Error Search
  • Cuvier Error Search (deprecated)
2025-01
Langsmith Integration & Python SDK v0.3
  • Langsmith integration for Enterprise partners
  • Python SDK v0.3 (simplified API, Anthropic support)