# codebot-ai

> Safe, local-first autonomous coding agent. Policy-governed, audit-trailed, sandboxed. Works with any LLM.

- **URL**: https://www.freshcrate.ai/projects/codebot-ai
- **Author**: Ascendral
- **Category**: AI Agents
- **Latest version**: `v2.10.0` (2026-03-22)
- **License**: MIT
- **Source**: https://github.com/Ascendral/codebot-ai
- **Homepage**: https://ascendral.github.io/codebot-ai/
- **Language**: TypeScript
- **GitHub**: 2 stars
- **Registry**: github
- **Tags**: `ai-agent`, `automation`, `autonomous-agent`, `claude`, `cli-tool`, `code-generation`, `coding-agent`, `coding-assistant`, `typescript`

## Description

Safe, local-first autonomous coding agent. Policy-governed, audit-trailed, sandboxed. Works with any LLM.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v2.10.0` | 2026-03-22 | Medium | ## What's New in v2.10.0  ### --solve: Autonomous Issue-to-PR Pipeline Point CodeBot at a GitHub issue, get back a reviewed PR with full audit trail. ``` codebot --solve https://github.com/you/repo/issues/42 ``` 8 phases: Parse → Clone → Analyze → Install → Fix → Test → Self-review → PR  ### Electron Desktop App - Signed, notarized, Gatekeeper-approved (macOS arm64) - 113MB DMG (down from 343MB) - Auto-restart on crash with exponential backoff - Network drop recovery with reconnecting overlay - |
| `v2.9.0` | 2026-03-19 | Low | ## CodeBot AI v2.9.0  Autonomous coding agent with governed execution.  ### Highlights - **--solve command**: Point at a GitHub issue → get a PR with full audit trail - **Constitutional safety (CORD)**: Every action goes through a safety layer - **32 tools**: File ops, git, web, browser, docker, SSH, and more - **Self-review**: Agent reviews its own diff before committing - **Audit trail**: Every phase logged, every decision traceable - **Electron desktop app**: Signed, notarized, Gatekeeper-app |
| `v2.8.0` | 2026-03-15 | Low | ## What's New  ### Dashboard Models Panel - VRAM detection card with real-time usage bar - Quantization advisor — select a model size, get recommendations based on available VRAM - Local model browser showing installed Ollama models  ### CodeAGI Continuous Mode - Auto-run mission cycles on a configurable timer (30s to 5m intervals) - SSE streaming for real-time phase updates - Error-based auto-stop after 2+ consecutive failures  ### Documentation Overhaul - Added "Who This Is For" section target |
| `v2.5.2` | 2026-03-05 | Low | ## What's New  ### Command Center (Dashboard) - **Terminal** — execute shell commands with live streaming output, command history - **Quick Actions** — 8 one-click buttons (Git Status, Run Tests, Git Log, Git Diff, Health Check, List Tools, List Files, NPM Outdated) - **Chat** — interactive AI chat with agent (`codebot --dashboard`) - **Tool Runner** — select any tool, fill parameters, execute with result display - **Standalone mode** — Terminal + Quick Actions work without agent connection  ### |
| `v1.4.3` | 2026-02-28 | Low | ## The Problem  During multi-tool interactions, CodeBot's message history could get corrupted, causing OpenAI to permanently reject all requests with:  ``` Invalid parameter: messages with role 'tool' must be a response to a preceeding message with 'tool_calls' ```  ## Root Cause  The context compaction code iterated message-by-message backward and could split `assistant + tool_response` groups in half. Example:  ``` [assistant with tool_calls: call_1, call_2]  ← DROPPED (budget exceeded) [tool: |
| `v1.4.2` | 2026-02-28 | Low | ## What's Fixed  **Message history corruption causing OpenAI 400 errors** — During multi-tool-call interactions, the message history could become corrupted (orphaned tool messages, duplicates), causing OpenAI to reject all subsequent requests with:  ``` Invalid parameter: messages with role 'tool' must be a response to a preceeding message with 'tool_calls' ```  The circuit breaker (from v1.4.1) would stop the loop after 3 attempts, but the session was permanently broken.  ## The Fix  Enhanced ` |
| `v1.4.1` | 2026-02-28 | Low | ## Bug Fix  **Fixed:** Agent was looping 50 times on non-retryable errors (missing API key, auth failure, billing issues) instead of stopping immediately.  ### What changed  - **Fatal error detection** — New `isFatalError()` recognizes permanent failures (missing API key, 401/403, billing, model not found) and stops the agent loop immediately - **Circuit breaker** — If the same non-fatal error repeats 3 times consecutively, the agent stops instead of burning through all 50 iterations - **Early A |
| `v1.4.0` | 2026-02-28 | Low | ## 15 New Tools (13 → 28 total)  CodeBot now has parity with top-tier coding agents. All tools are zero-dependency, using only Node.js built-ins.  ### Tier 1 — Intelligence \| Tool \| What It Does \| \|------\|-------------\| \| `git` \| status, diff, log, commit, branch, checkout, stash, push, pull, merge, blame, tag \| \| `code_analysis` \| Symbol extraction, find references, imports, file outline \| \| `multi_search` \| Fuzzy search across filenames + content + symbols with ranking \| \| `task_planner` \| Hie |
| `v1.3.0` | 2026-02-27 | Low | ## What's New  **9 stability fixes** that eliminate silent crashes during continuous operation.  ### Error Recovery - **Automatic retry** — 429 rate limits, 5xx server errors, and network failures (ECONNRESET, ETIMEDOUT) now retry with exponential backoff + jitter, respecting Retry-After headers - **Stream crash recovery** — if the LLM connection drops mid-response, the agent loop retries on the next iteration instead of dying - **Compaction fallback** — if LLM-powered context summarization fail |

## Dependency audit

- **Score**: 100/100
- **Total deps**: 13
- **Resolved**: 13
- **Unresolved**: 0
- **License conflicts**: 0
- **Warnings**: 0
- **Scanned**: 2026-06-01

## Citation

- HTML: https://www.freshcrate.ai/projects/codebot-ai
- Markdown: https://www.freshcrate.ai/projects/codebot-ai.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/codebot-ai/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._