buildwithnexus
Interactive AI agent orchestrator with intent-based planning, execution, and brainstorming modes
Why this rank:Recent releaseHealthy release cadence
Description
Interactive AI agent orchestrator with intent-based planning, execution, and brainstorming modes
Release History
| Version | Changes | Urgency | Date |
|---|---|---|---|
| v0.12.15 | ### Fixed - **Shift+Tab keeps your draft.** Cycling modes used to discard the composer, including the cursor position and any continuation lines entered with a trailing `\`. The draft, its lines, and the cursor now survive the mode change. Shift+Tab is ignored inside ordinary y/N and question prompts instead of cancelling them. - **Autocomplete replaces the whole token.** Accepting a completion with the cursor mid-token (for example `/he|lp`) produced `/helplp`. Tab and Enter comple | High | 9/8/2026 |
| v0.12.14 | Release v0.12.14. See CHANGELOG.md for details. ## What's Changed * fix(tui): comprehensive resolution of TUI audit findings by @geaglin in https://github.com/Garretts-Apps/buildwithnexus/pull/77 * fix: prevent /model menu duplication and increase local probe timeout by @geaglin in https://github.com/Garretts-Apps/buildwithnexus/pull/78 * fix: plan mode TUI rendering, typeahead preservation, and cancel safety by @geaglin in https://github.com/Garretts-Apps/buildwithnexus/pull/79 **Full Chang | High | 7/30/2026 |
| v0.12.6 | ### Added - **A killed TUI restores your terminal.** SIGTERM, SIGHUP, SIGINT, and SIGQUIT now run an async-signal-safe handler that leaves the alternate screen, shows the cursor, disables mouse/paste reporting, and restores the pre-raw terminal settings before exiting â no more `reset` after an external kill. Adds `libc` as a unix-only direct dependency (it was already in the tree via crossterm), making it six direct dependencies. - **`doctor` now probes your configured provider live. | High | 7/19/2026 |
| v0.11.4 | Gemma local-model support, from a real gemma-2-2b-it session on llama.cpp. ### Added - **Parse Gemma's `tool_code` tool-call format.** Gemma emits tool calls as a ```` ```tool_code ```` fenced Python call â `write_file("/p", """âĻ""")`, sometimes wrapped in `print(...)`. The harness only understood JSON/`<tools>`, so it treated the call as prose and (eventually) published an empty artifact. The recovery parser now handles the Python-call syntax: it unwraps `print()`, splits arguments | High | 7/7/2026 |
| main@2026-06-26 | Latest activity on main branch | High | 6/26/2026 |
| 0.8.7 | Imported from npm (0.8.7) | Low | 4/21/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| main@2026-03-17 | Latest activity on main branch | Low | 3/17/2026 |
| v0.4.0 | Tag v0.4.0 | Low | 3/13/2026 |
| v0.2.8 | Tag v0.2.8 | Low | 2/18/2026 |
| v0.2.7 | Tag v0.2.7 | Low | 2/18/2026 |
| v0.2.6 | Tag v0.2.6 | Low | 2/18/2026 |
| v0.2.5 | Tag v0.2.5 | Low | 2/18/2026 |
| v0.2.4 | Tag v0.2.4 | Low | 2/18/2026 |
| v0.2.3 | Tag v0.2.3 | Low | 2/18/2026 |
| v0.2.2 | Tag v0.2.2 | Low | 2/18/2026 |
| v0.2.1 | Tag v0.2.1 | Low | 2/18/2026 |
| v0.2.0 | Tag v0.2.0 | Low | 2/18/2026 |
Dependencies & License Audit
Loading dependencies...
Similar Packages
@hexitlabs/hexosHexOS â The operating system for AI-powered businesses. Deploy AI agent teams that work 24/7.main@2026-07-14
More in Frameworks
onnxruntimeONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
bamlThe AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)
pyodpsODPS Python SDK and data analysis framework
DrasilGenerate all the things (focusing on research software)