Download Latest Version
v0.9.1 source code.zip (7.4 MB)
Get an email when there's a new version of Prime Agent
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| latest.json | 2026-08-19 | 820 Bytes | |
| prime-agent-0.7.4.tgz | 2026-08-19 | 9.4 MB | |
| prime-agent-ai-0.7.4.tgz | 2026-08-19 | 539.1 kB | |
| prime-agent-core-0.7.4.tgz | 2026-08-19 | 58.7 kB | |
| prime-agent-tui-0.7.4.tgz | 2026-08-19 | 427.3 kB | |
| SHA256SUMS | 2026-08-19 | 364 Bytes | |
| stable | 2026-08-19 | 7 Bytes | |
| README.md | 2026-08-19 | 2.1 kB | |
| v0.7.4 source code.tar.gz | 2026-08-19 | 6.4 MB | |
| v0.7.4 source code.zip | 2026-08-19 | 7.1 MB | |
| Totals: 10 Items | 23.9 MB | 0 | |
- Fixed model searches ranking stronger matches ahead of weaker signed-in matches while preferring signed-in providers for equivalent results (#539 by @eliebak).
- Fixed large IPython variables repeatedly slowing later turns by excluding them from persistent snapshots and removing them when context is compacted.
- Fixed daemon socket paths being used verbatim in identity derivations: on supported platforms,
--daemon-socketspellings differing only by duplicate or trailing slashes now normalize to one canonical path, so worker-descriptor namespaces, daemon log files, and persisted descriptors agree. - Added a
thinkingoption torlm.runfor spawning subagents with an explicit reasoning level; invalid levels for the resolved child model fail spawn. - Changed opening the agents view (full or scoped) with a draft prompt to auto-stash the draft instead of refusing; the draft is restored into the editor when the session is reopened.
- Fixed Shift+Enter no longer inserting a newline in terminals that send a literal
\n(for example a Ghosttyshift+enter=text:\nmapping): the byte decoded asctrl+jand triggered the new edit-diff toggle instead of the editor newline. - Removed a system prompt paragraph referring to an async
bash()kernel helper and managed jobs that do not exist in the runtime. - Changed RLM guidance to orchestrate independent workers in parallel, use available async shell helpers safely, end the turn instead of sleeping, polling, or blocking on long awaits, provide proactive outcome-focused progress updates from root agents, and use simplified technical English for user-facing prose.
- Fixed new top-level daemon sessions inheriting an RLM child depth from the supervisor process.
- Fixed active goals stalling after a mid-goal automatic compaction when the previous continuation prompt was already running: only undelivered continuations deduplicate, so a fresh continuation is queued instead of being suppressed.
