TRAINING · OPEN SOURCE

Forge

RL environments for training AI agents on real-world apps

forge
$ forge run gmail --agent anthropic:claude-haiku

▸ Loading Gmail environment (34 emails, 19 contacts)...
▸ Running episode — step 12/50...
▸ Evaluating reward function...

✓ Reward: 0.91 · Policy: passed · Export ready
✓ Dataset saved → sft_pairs_episode_042.jsonl
THE PROBLEM

Training AI agents requires realistic environments

Teams building AI agents struggle to collect quality training data. Synthetic generation misses real app complexity; scraping is inconsistent and brittle. There's no standardized way to create controllable, observable environments where agents can explore, fail, and improve.

🌍
4

Environment Types

Gmail, Slack, CLI, Browser, ready out of the box

📦
7

Export Formats

SFT, DPO, GRPO, failure datasets, and more

🤖
5

Agent Adapters

Random, scripted, Anthropic, OpenAI, vLLM

CAPABILITIES

Everything you need to collect data

📧

Premade Environments

Gmail replica (34 emails, 19 contacts) and Slack replica (7 channels, 88 thread replies) ready to run, no config needed.

🔧

Custom Environments

Describe any app in plain English; 5 parallel LLM agents scaffold code, telemetry, state bridge, policy DSL, and reward function.

⚖️

Reward Engine

LLM-as-judge, sentence embeddings, ROUGE-L, and BLEU scoring with 6 built-in verifier types (Exact, Event, Temporal, Negative, Policy, Semantic).

📤

Dataset Export

7 formats: SFT pairs, preference pairs, GRPO rollouts, failure dataset, raw trajectories, rewards, verifier results.

🔁

Episode Replay & Branching

Re-run any recorded episode step-by-step; fork from any step and try alternate action sequences.

📊

Benchmark Suite

Fixed task suite across 2 domains (email, project management), 10 tasks, scores environments on coverage, reward density, dead-end rate, and action diversity.