Arcee.ai

Arcee returned Mergekit to LGPL v3 after its Business Source License period, citing adoption friction from legal review. Commercial and proprietary use is unrestricted; distributing modified copies of the library requires releasing those changes.

Arcee and Nous Research paired the Hermes agent with Trinity-Large-Thinking, published alongside a walkthrough for getting the harness installed and configured on Linux, macOS and Windows.

Trinity opens Arcee's open-weight mixture-of-experts line with Trinity-Mini at 26B parameters and 3B active over 128 experts, alongside a 6B Nano preview with 1B active. Weights are on Hugging Face, with a free access window on OpenRouter at a 131k context window.

Arcee engineers benchmark AFM-4.5B on Intel Xeon, AWS Graviton and Qualcomm CPUs to establish which configurations make CPU-only serving viable, covering the hardware and software improvements that close the gap for cloud and edge deployments.

How Differentiable Adaptive Merging replaces evolutionary model merging with learned per-column scaling coefficients over weight matrices, with the researcher explaining why the optimisation framing is faster and more predictable than parameter search.

Arcee's Orthogonal Matching Pursuit method transplants one model's tokenizer into another with no retraining, reconstructing unseen token embeddings from shared ones. Reported: 96% performance retention across families and vocabularies that overlap only 54%.

Arcee ships SuperNova-Medius, a 14B open-weight model distilled from Llama-3.1-405B across architectures, and MergeKit's author uses the release to lay out where synthetic-data, logit, and hidden-state distillation each break down.

What breaks when adapting an LLM to a domain: full-weight fine-tuning erodes general capability, real customer corpora are noisy, templated and narrow, and filling the gap with synthetic data brings its own grounding and alignment risks. Argues for smart filtering over volume.

Arcee is partnering with Bolt to train and evaluate future open-weight models on real developer sessions, giving opted-in Bolt Pro users 50x usage on models like GLM-5.3 and DeepSeek-v4-Pro for a month in exchange for using their building sessions as training data.

Arcee and Bolt.new launched Forge: opted-in Bolt Pro users get 50x usage with no daily caps on open-weight models like DeepSeek-v4-Pro, GLM-5.3, and Kimi-K3, while anonymized build sessions train Arcee's next open models.

MergeKit v0.1 drops the architecture allowlist. It merges any transformers-supported model including vision-language ones, adds a mergekit-pytorch path for raw PyTorch checkpoints such as diffusion and audio models, and makes the Arcee Fusion selective merge method public.

After close to 3 trillion tokens in 50 days, Arcee is applying what it calls lenient rate limits to the free Trinity Large Preview endpoint. Free access remains for now, with added capacity and a paid endpoint planned for workloads that need consistent throughput.

OpenClaw's 2026.4.7 release adds a bundled provider plugin spanning Arcee's full model catalog and OpenRouter, making Trinity-Large-Thinking a dropdown selection rather than a custom endpoint configuration.

Loka post-trained Arcee's 26B Trinity Mini into a science research harness: slash commands trigger fixed workflows, an internal critic stress-tests hypotheses against retrieved evidence, and ambiguous queries resolve identifiers against PubMed, UniProt and GEO before concluding.

Arcee's hosted API now serves GLM-5.3 and GLM-5.3-Flash, extending a catalog it opened two weeks earlier beyond its own Trinity line to DeepSeek, Kimi and Inkling. All of them sit behind a single endpoint and are callable from its nac agent for long-running, hands-off work.

Arcee's open models API beta widens past Trinity to serve DeepSeek-V4 Pro and Flash, GLM-5.2, Kimi-K3 and Thinking Machines' Inkling-Small, with per-million-token pricing listed for each and shipped alongside its open-source nac agent harness.

Arcee benchmarks its AFM-4.5B model on Intel Sapphire Rapids, AWS Graviton4 and Qualcomm Z1E processors at several quantizations, and explains what changed to make CPU serving viable: accelerated instruction sets, mature quantization and serving stacks, and smaller models.

Mergekit is now licensed under GNU LGPL v3, a change Arcee frames as returning the model-merging toolkit to its original terms and clearing up what users and contributors are permitted to do with it.

Arcee reports Trinity-Large-Thinking at 91.9 percent on PinchBench, the OpenClaw agent benchmark from Kilo Code, second to Claude Opus 4.6 at 93.3 percent. Input runs $0.25 per million tokens with cache reads at $0.06, and OpenRouter made it free for OpenClaw through April 5.

nac is an Apache 2.0 harness where an orchestrator dispatches work to isolated workers; each worker exits and drops its raw context, leaving a summary episode other threads can weave in. It ships an MCP server, alongside an Arcee API beta hosting several frontier open models.

An unflattering, blow-by-blow account of stretching AFM-4.5B from 4k to 64k context: which long-context papers survived contact with reality, why RULER alone misleads, and how merging and soups recovered short-context performance.

NAC v0.1.4 adds conversation forks: a finished chat prefix clones into an independent session keeping workspace, model, threads and steering, without duplicating the sandbox worktree. Stop now confirms model, tool, worker, MCP and command teardown before it reports a run cancelled.