iva

• Voice — voice, audio and video notes transcribed with Deepgram nova-3; auto-detects ru/uz/en.
• Vision — photos described by your provider's own vision model; no extra key, no extra bill.
• Rich replies — tables, checklists, collapsible blocks and formulas render natively in Telegram via Bot API 10.1 rich messages; plain formatting keeps its proven path, with a graceful fallback.
• Quiet update checks — once a day Iva checks for a newer stable release without spending model tokens. If one exists, Telegram offers Update or Later once; otherwise it says nothing.
• Layered memory — remembers across months, long after the chat window has scrolled away.
• Personal CRM — who your people are, what you agreed, when to follow up.
• Search by meaning — BM25 plus link-graph rerank, any language; optional vector mode with one key.
• Decision cards — what you chose, when and why; old versions stay in a dated History.
• Tasks & reminders — priorities, due dates and a morning digest.
• Web search — four pluggable providers: Tavily, Exa, Parallel or Brave.
• Google Workspace — Gmail, Calendar, Drive, Sheets, Docs and Tasks from chat via the gws CLI; installed for you, with a guided key setup right in the conversation.
• Skills & MCP — drop one file to add a procedure or connect an MCP server; keys stay in .env.
• Personal Telegram — userbot (beta) — read and send from your own account, not just the bot; connect by chat (QR, no terminal). Rough and buggy — opt-in, at your own risk. A server-side anti-ban guardrail (FloodWait compliance + randomized pacing + circuit-breaker) is enforced, not just advised. Details.
• Safe to forward — forwarded text, captions and voice transcripts pass an injection screen before the model reads them. A flagged message or transcript reaches the model tagged as data rather than as an instruction; for media captions the screen runs but the tag does not travel with it yet.
• Token accounting — every model step is logged; /usage reports it for free.

git clone https://github.com/smixs/iva-agent.git ~/iva
cd ~/iva && bash install.sh

The installer reuses the existing checkout instead of re-cloning, keeps .env and the vault untouched, and installs the same dependencies. A fork or a branch works through variables read at startup: REPO_URL=…, BRANCH=…, INSTALL_DIR=… (defaults: this repo, main, ~/iva). Details: docs/install.md.

24.08.2026

v0.3.29

• Install no longer loses agent-browser and gws on a fresh VPS: the verified download landed in a mktemp file with no extension, npm 11 read that path as a package directory and died with ENOTDIR … /package.json. The tarball now downloads into its own private directory under its published name (agent-browser-0.34.0.tgz, cli-0.22.5.tgz); the SHA-256 check still runs before anything reaches npm, and the directory is removed after (#197).
• The agent reads its memory again: 10-map.md told the model to call read_file with vault/summaries/daily/…, while the tool resolves a relative path against the vault root — the result was vault/vault/… and ENOENT on every day summary. Every model-facing memory path is now vault-relative (CORE.md, summaries/daily/…, cards/…, the same shape memory_search returns), the nightly rollup hands the model absolute paths, and a guard test fails on any instruction that brings the prefix back (#199).
• CORE.md is edited, not rewritten: the nightly rollup used to rewrite the whole file from the template, and a section the owner added by hand could vanish overnight. Now the rollup edits single lines only when the day produced a durable fact, preference, goal or lesson; a day with nothing new leaves the file byte-identical; sections outside the template stay verbatim. The «last day» pointer is written by code after the turn. If a ## heading present before the turn is gone after it, the previous file is restored and one Alert names the lost heading (#201).
• Forwarded messages carry their origin: a repost used to reach the model as the owner's own words. The first line of the text now says [forwarded from @user], [forwarded from channel Title (@name)] or [forwarded (hidden sender: Name)] — the same line in the context and in the daily log; source names are stripped of brackets and line breaks so a channel title cannot forge a label. The allowlist is untouched: access is still decided by the actual sender (#195).
• Three contributor fixes to the update rails: recovery keeps the permissions it captured, so a group-writable tree (664/775 under umask 002) no longer fails every iva update with git recovery snapshot permissions do not match and Rollback: FAILED (#196); a failed update drops its recovery stash the way a successful one does, so stale stashes stop piling up in git stash list (#200); the isolated build promotes .eve/agent-summary.json alongside .output, so /menu → Skills no longer says «Skill list is unavailable» after every update (#198).

19.08.2026

v0.3.28

• The update cleans up after itself: the disk keeps the running version and one rollback, everything else goes. Before a build only the running version stays — the build takes the rollback slot, so the peak is two versions (~400 MB each), not three. In the finish, removing old versions is the first step, ahead of npm i -g @googleworkspace/cli@latest, which downloads onto the same disk; a failed cleanup chore no longer cancels it. iva doctor removes leftovers of interrupted builds and surplus versions by itself, under the update lock, and prints versions on disk: N (current …, rollback …) — X GB free; with an update running it says version cleanup skipped, with a corrupt active.json it reports and deletes nothing. The cleanup before a build starts working from the update after this one — iva update runs on the installed CLI. Prompted by a test droplet with 8.7 GB that stalled on three copies of node_modules (#194). New troubleshooting section «Disk full during update», an honest disk line in install.
• The promoted runtime carries every source tree: the stable runtime snapshot copied agent/ and scripts/ by hand, packages/ never reached it, and on an install with a non-empty custom layer the agent died with [UNRESOLVED_IMPORT] on agent/lib/data-dir.ts in a restart loop. One list now — RUNTIME_SOURCE_TREES — feeds both the snapshot and the replica smoke, the layout digest moves to v3 so a runtime staged without packages/ rebuilds itself, and a guard test resolves every import of those trees and fails on a tree the snapshot would leave behind (#192, #191).
• Timezones come back in canonical spelling: Intl accepted europe/moscow in .env, systemd rejected OnCalendar=*-*-* 05:00:00 europe/moscow, and the nightly timer never came up. The validator now returns what Intl resolves — Europe/Moscow; aliases canonicalize (US/Pacific → America/Los_Angeles); property tests pin idempotence and insensitivity to case and padding (#190).
• A vision model per provider: instead of a constant in code, a variable in .env each, blank meaning the provider default — OLLAMA_VISION_MODEL (gemma4:31b), OPENCODE_VISION_MODEL (qwen3.7-plus), OPENROUTER_VISION_MODEL (google/gemini-2.5-flash); Codex has none, the subscription is multimodal. iva config asks for the vision model right after the text model and writes it next to *_MODEL. The OpenCode Go default comes from live runs on 18.08: gpt-5.6-luna answers 400 to any image, minimax-m3 wraps its answer in <think> inside content, qwen3.7-plus returns a clean description with OCR in 4–6 seconds.
• Three Telegram fixes: the Stop button only in private chats — its callback has been rejected in groups since the last release, and the button hung there dead. Messages buffered during a rolling update pass the inbound gate with the same warning to the model and the same [security] inbound flagged line as fresh ones — the verdict used to be ignored. Prose that looks like a code placeholder (the price is 50 dollars, tables with padded numbers) is no longer cut out of an HTML reply: the placeholder moved to the Private Use Area, such code points from outside are stripped first, and a seeded property test walks digits, space runs and code spans mixed in prose.

18.08.2026

v0.3.27

• MCP servers of a plugin, both transports: streamable-http and sse in mcp.json become a generated eve connection mcp-<name>--<server>, and ${VAR} in a header is filled at run time from data/custom/plugins/<name>.env, so no token is baked into a build. stdio runs as the systemd unit iva-mcp-<name>-<server>.service behind Iva's own MCP proxy (services/mcp-proxy/, @modelcontextprotocol/sdk): the agent reaches it over 127.0.0.1:<port>/mcp with a bearer, and the token lives in data/plugin-data/<name>/mcp-<server>.token at mode 0600. The server sees only PATH, HOME, PLUGIN_ROOT, PLUGIN_DATA, its own env from mcp.json and <name>.env — nothing of the agent's environment reaches it. A second switch joins the first: trusted, through iva plugin trust | untrust, and add prints the processes and asks Start these processes on this machine? [y/N] (--trust answers yes; a shell without a terminal answers no). Ports are handed out from 8730, once, and stay until the plugin is removed. Proven end to end against a real stdio server and a real client from the SDK, not fakes.
• Plugin services: sh.iva/services/<svc>/service.json with {command,args,port} becomes the unit iva-plugin-<name>-<svc>.service — env IVA_SERVICE_PORT, IVA_DATA_DIR, PLUGIN_ROOT and PLUGIN_DATA, the service's own folder as the working directory, started only while the plugin is enabled and trusted. iva plugin update restarts the units of a plugin whose content changed, iva update brings them back right after the flip, and iva doctor lists the units, prints is-active and calls GET /health on every MCP proxy. sh.iva/ is now two kinds: an eve Extension (sh.iva/package.json, built into a version) and services, which never rebuild one.
• The default Marketplace is live — smixs/iva-plugins: the list sits at github.com/smixs/iva-plugins and carries two plugins. trace is the Trace viewer: the schema of Iva with the path of a turn lit across it, the feed of turns, replay at ×1, ×2 and ×4, tiles for today, 7 and 14 days; it listens on loopback only, and iva trace open prints the ready ssh tunnel command. hello is the demo code plugin authors copy: one skill, one tool. Three commands to get there: iva plugin add trace, iva plugin trust trace, iva trace open. Checked live from the public list: list --available, add trace pinned to a sha, update, remove.
• Plugin docs: docs/plugins.md (Russian: docs/ru/plugins.md) — what a plugin is, how to install one (a folder, owner/repo[/subdir][@ref], a git URL or a name from a Marketplace), how enabled differs from trusted, what iva update does to plugins, how to write your own (skills, an Extension under sh.iva/, mcp.json, services) and what you risk; SECURITY.md gains a Plugins section. Also: the iva plugin CLI is split into modules with no command changed, and on a development checkout add and remove of a code plugin stop promising a build that never happened and say plainly that no version was built there.