gitclaw
A universal git-native multimodal always learning AI Agent (TinyHuman)
Why this rank:Strong adoptionRelease freshnessHealthy release cadence
Description
A universal git-native multimodal always learning AI Agent (TinyHuman)
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| v1.4.3 | ## What's New Fixes the **\"Your session hit the maximum duration of 60 minutes\"** failure in voice mode â previously, once OpenAI terminated the Realtime session, every subsequent message returned \"server had an error while processing your request\" and the agent was stuck until restart. ### Proactive refresh On \`session.created\`, a 55-minute timer is armed. When it fires, the adapter tears down the WS and opens a fresh one with the same instructions, tools, and voice. Users notice a sub- | High | 4/22/2026 |
| 1.4.1 | Imported from npm (1.4.1) | Low | 4/21/2026 |
| v1.4.2 | ## What's New ### New \`edit\` built-in tool The agent can now modify files without rewriting them in full. Works on both the local filesystem and inside the E2B sandbox. **Modes:** - **Exact string replacement** (default) â must match uniquely; errors with a clear message if not found or ambiguous - **replace_all** â replace every occurrence - **regex** â treat \`old_string\` as a JavaScript regular expression; \`new_string\` can use \`\$1\`-style backreferences, and custom flags (\`i\`, \`m\ | High | 4/20/2026 |
| v1.4.1 | ## What's New Enhances the Logs UI with much deeper server-side instrumentation so that even the smallest error becomes visible. ### Global safety net - `uncaughtException`, `unhandledRejection`, and Node `warning` handlers â captures crashes that would otherwise disappear silently - Error objects now logged with full stack traces ### HTTP layer - Every `/api/*` request logged with method, path, status, and duration - All 4xx/5xx responses logged at the corresponding level - `jsonReply` auto- | High | 4/17/2026 |
| v1.4.0 | ## What's New ### Unified Logs Tab A new **Logs** tab in the web UI that surfaces all server-side logs in real time â voice, Telegram, WhatsApp, triggers, SDK, scheduler, and system events. **Features:** - Real-time log streaming via WebSocket - Filter by source (voice, telegram, whatsapp, triggers, sdk, scheduler, system) - Filter by level (info, warn, error) - Full-text search - Auto-scroll with toggle - Color-coded source badges and level-based message coloring - REST endpoint (`GET /api/lo | High | 4/17/2026 |
| v1.1.0 | ## What's New - **Cron Scheduler** â schedule prompts to run on a cron expression or one-time datetime, with JSONL logging, repeat/once modes, and auto-disable for one-shot jobs - **Scheduler UI** â new Scheduler tab in the voice dashboard with form, preset cards, toggle/run/delete controls - **6 REST API endpoints** â `/api/schedules/list`, `save`, `delete`, `toggle`, `run`, `logs` - **Installer Auto-Resume** â returning users with an existing `~/assistant` setup skip the interactive wizard an | Low | 3/15/2026 |
| v1.0.0 | ## SkillsFlow â v1.0.0 (Major Release) ### What's New - **SkillFlows Builder** â Visual workflow builder with a skills panel, step cards, and arrow connectors - **Drag-and-Reorder** â Drag step/gate cards to rearrange flow order with a blue drop indicator - **Approval Gates** â Pause flows and request approval via Telegram or WhatsApp before continuing - **Speaker Mute** â New button to mute/unmute agent audio output instantly - **New Workflow Button** â Quick-start a fresh workflow from the Sa | Low | 3/15/2026 |
| v0.4.1 | ## What's Changed - Removed all scaffolding artifacts (flappy bird, calculator, hello, jumping ball, architecture diagrams, requirements.txt) - New `install.sh` with pixel sprite banner and two setup modes: - **Quick Setup** â OpenAI + Anthropic + optional Composio, launches in 30 seconds - **Advanced Setup** â voice adapter, model, project dir, Composio, Telegram, port selection - Auto-opens browser on launch (macOS, Linux, Windows) - Saves API keys to `.env` for future runs ### Full inst | Low | 3/14/2026 |
| v0.3.0 | ## Local Repo Mode with Session Branches Adds `--repo <url> --pat <token>` to auto-clone a GitHub repo locally, create a session branch, run the agent, auto-commit changes, and push the session branch. ### Features - **CLI**: `gitclaw --repo <url> --pat <token> "prompt"` â clones, branches, runs, commits, pushes - **Session resume**: `--session gitclaw/session-<id>` checks out existing branch with full context - **SDK**: `query({ repo: { url, token } })` â same flow programmatically - **Token | Low | 3/4/2026 |
| v0.2.0 | ## What's new **Sandbox mode** â Run agent tools inside an isolated E2B cloud VM via [gitmachine](https://github.com/open-gitagent/gitmachine). The agent (LLM calls) still runs locally; only tool execution is remote. All changes are automatically committed to a session branch. ### Usage **CLI:** ```bash export E2B_API_KEY="..." export GITHUB_TOKEN="ghp_..." gitclaw --dir ~/my-project --sandbox ``` **SDK:** ```typescript import { query } from "gitclaw"; for await (const msg of query({ prom | Low | 3/4/2026 |
| v0.1.0 | # Gitclaw v0.1.0 **A universal git-native AI agent framework.** Your agent lives inside a git repo â identity, rules, memory, tools, and skills are all version-controlled files. ## Highlights ### CLI + SDK - **CLI** with REPL and single-shot (`--prompt`) modes - **Programmatic SDK** â `query()` returns an `AsyncGenerator<GCMessage>` for streaming agent events - **`tool()` helper** â define custom tools the agent can call ### Git-Native Architecture - `agent.yaml` for model, tools, and runti | Low | 3/4/2026 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
More in AI Agents
hermes-agentThe agent that grows with you
awesome-copilotCommunity-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.
CopilotKitThe Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
e2bE2B SDK that give agents cloud environments