WIP Local-first AI platform: chat, fine-tune (LoRA/QLoRA), post-train, quantize, compress, and export open models on your own GPU — Forge UI + CLI, no cloud required. No crypto token
Release v0.13.0 — TUI removed, agentic CoT off the TTFT path, chat hang fixed
Github Release · Source verified
## Summary Changes since **v0.12.0** (14 commits / PRs [#529](https://github.com/Legendarylibr/SeisoLocalAI/pull/529)–[#533](https://github.com/Legendarylibr/SeisoLocalAI/pull/533)). The **terminal UI (TUI) is removed**: `seiso tui`, its install path, harnesses, and tests are gone — the Tauri desktop app (`start`) and web UI (`seiso forge`) are the only interfaces. The **agentic chain-of-thought path was reworked** so thinking stays off the TTFT (time-to-first-token) critical path, and the swarm now escalates sensibly (verify, add subagents, prompt continuation). A **chat hang and slow token d
Summary Changes since v0.11.0 (6 commits / PRs #526–#528). The Tauri desktop app becomes the only start path: start now builds and launches the native Seiso Forge desktop wrapper instead of opening a browser (web UI seiso forge and TUI seiso tui remain CLI commands). The desktop wrapper was fixed end-to-end so it actually runs and renders, the wrapper and startup path were security-hardened from a dedicated review, and the security-critical logic is now formally verified in Lean 4 + mathlib4. What's new Tauri desktop app as the default startup path (#526) - start /
v0.11.0 — Tauri desktop wrapper with swarm subagent orchestration
Github Release · Source verified
Summary Changes since v0.10.0 (5 commits / PR #525). A native Tauri 2 desktop wrapper lands for the Forge UI: the React frontend now runs in a system webview as a real desktop app (macOS + Linux), with a Rust host that orchestrates Seiso subagents. The host adds a swarm orchestrator with resource limits, stall detection, resume injection, completion verification, and result aggregation across subagents. What's new Tauri desktop wrapper (#525) - Tauri 2 app wrapping the forge-ui React frontend in the system webview (1280×800 window, system tray, CSP locked to localhost)
Summary Changes since v0.9.0 (95 commits / PRs #485–#524). The roadmap's local agentic OS becomes executable: a kernel that decides where work runs (local → mesh → pay → ask human), routes each step to a model, and runs a plan/act/verify/receipt harness. A new x402 EVM payments rail lands with USDC on 30+ chains. start returns to launching the Forge web UI by default (TUI stays opt-in), and the TUI gains keyboard navigation, Nostr auth, agent harnesses, and readable model names. Project direction Seiso stays a local-first stack: chat, fine-tune, post-train, compress
v0.9.0 — terminal UI default, security harden, native Linux install
Github Release · Source verified
Summary Changes since v0.8.0 (43 commits / PRs #464–#484). start no longer opens a browser. The default workspace is seiso tui: a Forge-shaped terminal UI with live Hugging Face Hub search, local chat, and studio command launch. The React Forge app remains available as an opt-in API (SEISO_UI=forge start or seiso forge). This release also clears several open dependency CVEs (PyJWT instead of python-jose/ecdsa, cryptography 50), hardens tool/KB injection defenses, and fixes native Linux install/start loops. Project direction Seiso stays a local-first stack: chat, fine-
Summary Changes since v0.6.0 (26 commits / PRs #442–#447). Project direction Seiso stays a local-first Forge + CLI stack: chat, fine-tune, post-train, compress, and export on your hardware. The product spine is still self-hosted training and inference. The longer arc is optional coordination and payment rails that stay opt-in and fail-closed: 1. Human UI vs agent surfaces — Forge Train stays the human path; Buzz-agent / mesh orchestration is a separate, gated surface so OS hostnames and unsigned chatter cannot become trust. 2. Nostr as the trust fabric for agents — me
Summary Changes since v0.5.0 (19 commits). Limitations — not functional yet, do not use Treat these as docs / scaffolding only. Do not run them for production work, real funds, or trusted multi-node jobs: | Surface | Flag | Status | |---------|------|--------| | Sats marketplace (seiso pay) | SEISOALLOWPAY=1 | Scaffolding only. Live Ark pay-in / Bark–Second settlement is not wired. Faucet (SEISOPAYFAUCET=1) or simulated ledger only for local smoke tests. | | Buzz mesh (seiso mesh) | SEISOALLOWMESH=1 | Experimental peer coordination scaffolding. Not rea
SeisoLocalAI v0.2.0 Second release since v0.1.0 (2026-06-19). ~700 commits and 90+ merged PRs focused on making native Linux NVIDIA chat stable, long replies finish reliably, training/SLIME work, and the product story clearer. Highlights Long-form chat (multi-pass, OOM-safe) - Dynamic multi-pass auto-continue so long answers (songs, papers, essays) finish without one huge completion that can OOM (#340 and earlier long-reply work: #323–#326). - Per-pass completion stays OOM-clamped (often ~512–768 tokens on native Linux NVIDIA); total reply budget scales with request, long-form
SeisoLocalAI v0.1.0 Initial public release of SeisoLocalAI, a local AI forge for installing, launching, and managing local model workflows. Highlights - One-command Linux/macOS installer. - Forge web UI with local onboarding. - Local model chat and model hub workflows. - Training, compression, export, and quantization tools. - Installer doctor for guided troubleshooting. - Stable install completion screen with the Forge URL. Notes This is the first versioned release. Expect rapid iteration as the installer, Forge UI, and local model workflows continue to improve.
