● Autonomous research agents that learn from runs

Give your research agent a second brain

LoopGraph is the memory layer for autonomous ML research. It remembers every experiment, ranks methods by what actually worked, and turns papers into the next winning edit.

Join the waitlist See benchmarks

~12

experiments / hour unattended

10.5–13.0%

fewer tokens vs. baseline

9.5–17.3%

faster wall-clock time

FTS5 + SQLite

local, auditable experiment memory

Most agents forget everything

Today’s coding agents start from scratch on every run. Grep is useful, but it is not memory: agents need active retrieval, code maps, provenance, and a record of which ideas worked.

Re-running failed ideas

Without memory, agents repeat experiments that already flopped.

Literature stays separate

Papers live in PDFs; agents can’t turn “use SwiGLU” into a working code change.

No provenance

When something works, no one knows which method or prompt caused it.

# Without LoopGraph: every run is a blank slate
agent.run()# propose → edit → train → evaluate → forget# With LoopGraph: every run learns from the last
agent.use(LoopGraph())# retrieve ranked methods → edit → train → log → improve

How it works

LoopGraph wraps your existing training loop and adds a retrieval layer that gets smarter with every experiment.

Seed the knowledge base

Ingest papers from arXiv or GitHub, or use the curated method pack covering SwiGLU, GQA, Muon LR, sliding-window attention, and more.

Run experiments

The agent edits train.py, trains for a fixed 5-minute budget, and logs the result to results.tsv and ResearchFS.

Rank what works

ResearchFS scores each method by success rate, BPB delta, query fatigue, and recency — so the agent reuses winners.

Keep improving

Every retrieval, outcome, and token cost is stored locally. The next experiment starts smarter than the last.

Meet ResearchFS

A local SQLite knowledge store with full-text search, empirical scoring, and an agent-native SDK. It turns a passive code search into active experiment memory.

🔍

FTS5 hybrid search

Combine full-text search with empirical rankings to surface the right method at the right time.

📊

Success-weighted scoring

Methods are ranked by prior BPB improvement, win rate, and fatigue — not just keyword match.

🔗

Full provenance

Every method links back to its paper, chunk, retrieval event, and experiment outcome.

# Query ResearchFS from your agent
from loopgraph import ResearchFSClient

client = ResearchFSClient("researchfs.db")
context = client.suggest_query(
    goal="improve validation bpb",
    current_code=train_py
)
# Returns ranked method pack + experiment brief

● Benchmarks from local smoke-test runs

Benchmarks: faster, cheaper, and honest about model quality

LoopGraph was compared against a baseline autonomous agent on the nanochat BPB benchmark. Same run harness, same fixed training budget; one agent received ResearchFS retrieval context and one did not.

GPT-4o-mini BPB delta

+0.02454

LoopGraph best BPB: 2.180112 vs. baseline 2.204652. Lower BPB is better.

Token savings

10.5–13.0%

20,986 vs. 24,127 tokens on GPT-4o-mini; 28,431 vs. 31,755 on GLM 5.2.

Wall-clock savings

9.5–17.3%

LoopGraph completed faster across both comparison runs.

Query reuse

Run 3

ResearchFS reused the prior query MLP SwiGLU during the GLM run.

Run	Baseline best BPB	LoopGraph best BPB	Tokens saved	Time saved	Outcome
GPT-4o-mini	2.204652	2.180112	13.0%	17.3%	LoopGraph wins BPB, tokens, and time
GLM 5.2	2.128834	2.153019	10.5%	9.5%	Baseline wins BPB; LoopGraph wins efficiency

Honest read: these are local agent-loop smoke tests, not SOTA claims. Published B200 baselines such as Recursive’s optimized_from_karpathy report mean BPB around 0.9109, while these quick local LoopGraph runs are around 2.13–2.20. The benchmark signal today is efficiency and retrieval behavior; the next milestone is closing the quality gap.

Built for researchers, not tourists

⚡

Single-GPU real training

Runs on real PyTorch + nanochat, not a toy environment. Tested on H100; MPS/CPU fallbacks included.

🔒

Local-first memory

Your experiment history, papers, and API calls stay in a local SQLite database — no cloud lock-in.

🧩

Provider agnostic

Plug in OpenAI, OpenRouter, Venice, or local models. Switch models without rewriting the loop.

🧪

Tested retrieval logic

1,693 lines of tests cover parsing, ranking, fatigue, deduplication, and harness-agent behavior.