# Hermes Agent Features and Practical Usage 🚀 Pick up exactly where you left off with a single command. Hermes Agent Sessions automatically record, resume, and search every conversation, forming the backbone of long-running agent operation. 📌 Title and Feature URL Title: Sessions URL: 📝 Overview Sessions automatically save every interaction, whether from CLI, Telegram, Discord, Slack, or other platforms. Full message history is persisted to SQLite, so you can resume past work or surface old exchanges via full-text search. Because sessions are tracked per platform, each chat naturally keeps its own context. 🔧 How It Works - History lives in `~/.hermes/state.db` (SQLite, WAL mode), tracking metadata, full message history, token counts, and an FTS5 full-text search index. - Only the current conversation window loads into active context, not every historical byte. Images become descriptions, audio is transcribed, and documents are summarized rather than re-sent. - After the first exchange, a background auxiliary model auto-generates a descriptive 3-7 word title with no added latency. - Sessions are keyed deterministically by source, with distinct formats for DMs, groups, and threads. 🛠 Practical Usage - Resume the latest CLI session: `hermes --continue` (or `-c`); resume by title with `hermes -c "project name"`, or by ID with `hermes --resume `. - List/export/manage: `hermes sessions list --limit 50 --source telegram`, `hermes sessions export backup.jsonl`, `hermes sessions prune --older-than 90 --yes`, `hermes sessions stats`. - Manual naming: `/title my project` in chat, or `hermes sessions rename "new title"`. - The agent itself uses the `session_search` tool (FTS5) and auto-references past chats when you say things like "remember when." - Hand off an active CLI conversation to a messaging platform with `/handoff telegram`, preserving the full transcript. 🎯 Use Cases - Resume yesterday's refactor with all prior context intact. - Quickly recall "what did we decide back then" via full-text search. - Keep separate context per entry point (Telegram, Discord) to avoid crosstalk. - Use it as a work-history database for long-running agents. ⚠️ Caveats - Auto-titling runs only once per session and skips if a title already exists. - Media bytes are never re-sent; only derived text or file paths persist in later context. - Auto-pruning (` is disabled by default; active sessions are never pruned regardless of age. - On non-thread platforms with shared group home channels, genuinely shared group chats aren't handled ideally. #HermesAgent# #AIAgents#

# Hermes Agent Features and Practical Usage 🚀 For when you don't want the conversation to stop while the agent works. The modern TUI offers non-blocking input, mouse support, and rich overlays so you can watch long tasks and drop in extra instructions. 📌 Title and Feature URL Title: TUI (Ink terminal UI) URL: 📝 Overview The TUI is a modern terminal UI for Hermes, launched as a subprocess from the Python CLI. It is Node.js-powered (≥20) and shares the same Python runtime, sessions, and slash commands as the classic CLI, while delivering a cleaner, more responsive experience. 🔧 How It Works ・It paints an instant first frame for a non-frozen startup, uses differential updates to prevent flicker during streaming, and provides rich modal overlays for model picking, session selection, and approval prompts. ・Non-blocking input lets you queue messages before the session is ready, and mouse selection uses uniform background highlighting instead of terminal inverse video. ・It renders LaTeX math, both inline (`$E = mc^2$`) and block (`$$...$$`). ・A status line narrates state (starting agent… / ready / thinking… / running… / interrupted) plus working directory with git branch, elapsed time, auto-compression count, active `/background` tasks, and a YOLO warning badge. 🛠 Practical Usage ・Launch with `hermes --tui`, resume the latest with `hermes --tui -c`, resume a specific one with `hermes --tui -r `, or force classic CLI with `hermes --cli`. ・To default to it, set the env var `HERMES_TUI=1` or `display.interface: tui` in `~/.hermes/config.yaml`. ・TUI-specific slash commands are plentiful: `/model` (picker with per-provider cost hints), `/sessions` or `/switch` (live session switcher), `/skin` (live theme preview), `/details` (toggle tool detail), `/agents` or `/tasks` (observability overlay with a subagent tree), `/mouse`, and `/reload`. ・Press `Ctrl+X` to open the live session switcher and run multiple concurrent sessions within one terminal. 🎯 Use Cases ・Watch a long task progress in the live panel while dropping in mid-run instructions via non-blocking input. ・Dispatch and orchestrate many concurrent agent sessions from a single terminal. ・Survive SSH disconnects by auto-resuming with `HERMES_TUI_RESUME`. ⚠️ Caveats ・Node.js ≥20 is required (verified by `hermes doctor`), and the first launch installs TUI Node dependencies into `ui-tui/node_modules` once. ・A TTY connection is assumed; pipes or non-interactive environments fall back to single-query mode. ・It cannot attach to a remote gateway (the TUI spawns its own in-process gateway). Light-theme detection relies on `COLORFGBG` or OSC 11 probes, which not all terminals support. #HermesAgent# #DevTools#

# Hermes Agent Features and Practical Usage 🚀 The CLI is the developer's daily window into the agent. Just type `hermes` in your repo and you get interactive chat, slash commands, and one-shot execution all in one. 📌 Title and Feature URL Title: CLI URL: 📝 Overview The Hermes CLI is a terminal chat interface. It shows a conversation stream, a fixed input prompt, and a status bar with the current model and token usage, letting you fine-tune behavior with slash commands as you work. Beyond interactive mode it supports single-query runs and session resume. 🔧 How It Works ・Launch modes include interactive (`hermes` or `hermes chat`), single-query (`hermes chat -q "..."`), and resume (`hermes --continue` / `hermes --resume `). ・The status bar shows model name, token usage (e.g. 12.4K/200K), a color-coded context fill bar, estimated cost, compression count, background task count, and elapsed time. ・Slash commands are rich: `/model` (switch model), `/personality` (helpful, concise, technical, teacher, and more), `/voice on|off|tts`, `/reasoning high`, `/background `, `/sessions`, `/usage`, `/tools`, `/status`. ・Long conversations auto-summarize (compress) as they near the context limit, by default keeping the first 3 turns and last 20 turns and summarizing the middle. 🛠 Practical Usage ・Launch flags shape behavior: `--model` / `--provider` to pick a model, `-s` (`--skills`) to preload skills, `-w` for an isolated git worktree, `--tui` for the modern UI, and `--yolo` to auto-approve tool calls. ・Multiline input is `Alt+Enter` / `Ctrl+J`, external editor is `Ctrl+G`, and interrupt is `Ctrl+C` (double-press within 2s to force exit). ・Define LLM-free shell commands under `quick_commands` in `~/.hermes/config.yaml` and invoke them like `/status`. ・Set `busy_input_mode` to steer to inject input into the running turn via `/steer` while the agent works. 🎯 Use Cases ・From a repo, ask "find why the tests fail and fix them," then adjust with `/model` or `/reasoning` as it runs. ・Spin up parallel, isolated sessions with `/background` to progress separate tasks at once. ・Call `hermes chat -q "..."` one-shot from scripts or pipelines. ⚠️ Caveats ・`Shift+Enter` newlines are terminal-dependent; standard Windows Terminal and macOS cannot distinguish it from Enter. ・`/background` sessions are fully isolated from the main conversation history and share none of the foreground context. ・The CLI strips markdown fences and formatting wrappers from final replies for readability (code blocks and lists remain). Voice mode requires a supported terminal. #HermesAgent# #DevTools#

# Hermes Agent Features and Practical Usage 🚀 More than remembering facts, this memory continuously infers who you are from conversation. The result is an agent that understands you, getting more on-target the longer you use it. 📌 Title and Feature URL Title: Honcho Memory URL: 📝 Overview Honcho is an AI-native memory backend that goes beyond simple key-value storage. After each turn it performs "dialectic reasoning" to automatically derive insights about your preferences, communication style, goals, and behavioral patterns, building a user model that deepens over time. 🔧 How It Works ・Dialectic reasoning is multi-pass analysis: Pass 0 produces an initial assessment, Pass 1 self-audits for gaps, and Pass 2 reconciles contradictions into a final synthesis (depth 1-3). ・New users get cold-start queries probing general preferences and goals; returning users get warm-session queries prioritizing current context. ・Where built-in memory is manually curated static facts, Honcho maintains server-side profiles with automatic reasoning, enabling semantic search over conclusions and multi-agent peer isolation. ・Five tools integrate: honcho_profile (read/update peer identity cards), honcho_search (semantic search over memory and conclusions), honcho_context (retrieve session context with summaries), honcho_reasoning (synthesized reasoning at a chosen depth), and honcho_conclude (create/delete conclusions, useful for PII management). 🛠 Practical Usage ・Run `hermes memory setup honcho` for guided setup; config is written to `~/.honcho/config.json` (global) or `$HERMES_HOME/honcho.json` (per-profile). ・Key config keys: `contextCadence` (base-context refresh interval), `dialecticCadence` (LLM reasoning interval), `dialecticDepth` (multi-pass depth), `recallMode` (hybrid / context / tools), `writeFrequency` (async / turn / session), plus `apiKey` / `peerName` / `aiPeer` / `workspace`. ・In the default hybrid mode, base context and dialectic supplements inject into the system prompt automatically while tools stay available. ・Once Honcho is active, subcommands like `hermes honcho status` become available. 🎯 Use Cases ・As a long-term assistant, track a user's working preferences across months. ・Keep a coding assistant and a personal assistant talking to the same user with independent models, preventing context bleed. ・Reduce repetitive topic recaps and raise suggestion accuracy via session-scoped injection. ⚠️ Caveats ・Cost scales with reasoning depth (depth 2-3 means more LLM calls; balance via cadence settings). ・New peers need a background prewarm; if it doesn't complete in time, a bounded synchronous fallback applies. ・In recallMode, tools mode gives the agent control but needs explicit reasoning calls, while context mode hides tools and reduces flexibility. State is server-side, so migrating from file memory requires a data export. #HermesAgent# #Memory#

# Hermes Agent Features and Practical Usage 🚀 Five minutes from install to your first real conversation. Have the agent read files, run commands, and search the web by handing it an actual task right away. 📌 Title and Feature URL Title: Quickstart URL: 📝 Overview The Quickstart walks you from a fresh install to a working first conversation. You launch with `hermes` or `hermes --tui` and exercise core abilities: inspecting a repo, executing commands, and searching the web. Its guiding principle is to get one clean conversation working before layering on anything else. 🔧 How It Works - Launch via the classic CLI `hermes`, or the modern TUI with modal overlays `hermes --tui` (recommended). - Run the setup wizard with `hermes setup`; pick a model interactively with `hermes model`. - Resume your most recent session with `hermes --continue` (short form `hermes -c`). - Diagnose configuration issues with `hermes doctor`. - Capabilities demonstrated include file reading, terminal command execution (with approval), web search via the Tool Gateway, and multi-turn conversations. 🛠 Practical Usage - Start with specific, verifiable prompts. Example: "Summarize this repo in 5 bullets and tell me what the main entrypoint is." - Confirm file reading with something like "Check my current directory and tell me what looks like the main project file." - Try "Help me set up a clean GitHub PR workflow for this codebase" to see command execution and the approval flow together. - Type `/` mid-conversation for an autocomplete menu of slash commands: `/help` (commands), `/tools` (available tools), `/model` (switch models), `/save` (save the conversation). 🎯 Use Cases - Right after install, double as a smoke test by asking for a repo summary or file inspection. - Feel out the command-approval flow on a real task to calibrate how much you delegate. - Switch models and tools via slash commands as you settle into your workflow. ⚠️ Caveats - Hermes Agent requires a model with at least 64,000 tokens of context; avoid models that are too small. - The guide stresses getting basic chat working first, then adding gateways, skills, or automation. - Command execution involves agent approval, so watch the approval behavior closely on your first run. #HermesAgent# #AIAgents#

hermes agent is already the best on local models. but i'm working on more edges to make it fly even harder. before that, if your agent keeps crashing on local inference here's what to check: > max_turns: default is tuned for fast frontier models. bump from 30 to 50. slow local models need more breathing room per agentic loop. >gateway_timeout: raise from 600 to 1200. local inference at 12-17 tok/s will timeout silently and look like crashes. > context accumulation: auto-reset is off by default. your session grows until you /reset. long convos choke the agent. reset between major tasks. if you're running anything under 20 tok/s locally, these three settings are the difference between "broken" and "flying." tune your config before you blame the tool.

Hermes Agent is now #1# on the Global @OpenRouter token rankings. While our journey together has just begun, we'd like to take this opportunity to thank our contributors, supporters, and users for all they have done to get us this far.