@ftarganski/omni-ai 1.1.10 → 1.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +12 -1
- package/dist/cli/bin.js +1043 -155
- package/dist/history.d.ts +1 -0
- package/dist/history.js +545 -0
- package/dist/index.d.ts +1 -0
- package/package.json +10 -5
package/README.md
CHANGED
|
@@ -27,6 +27,7 @@
|
|
|
27
27
|
- **21 ready-made agents** — backend (NestJS), frontend (React), UX audit, QA validation
|
|
28
28
|
- **Composable skills** — 20+ tools (filesystem, git, HTTP, accessibility audit, image analysis) that agents call as needed
|
|
29
29
|
- **Session memory** — SQLite-backed persistent sessions with semantic search and token compaction
|
|
30
|
+
- **Third-party agent history** — import and search local history from Claude Code and Codex, scoped to your current project by default
|
|
30
31
|
- **Extensible** — define custom agents in YAML, skills in TypeScript, providers via `IProvider`
|
|
31
32
|
- **MCP-compatible** — expose skills as MCP tools or consume any MCP server as skills
|
|
32
33
|
|
|
@@ -252,7 +253,8 @@ Tokens: 18,400 input · 5,200 output · ~$0.084
|
|
|
252
253
|
| `omni watch <agent> "<prompt>"` | Re-run an agent automatically on file changes |
|
|
253
254
|
| `omni eval <agent> <dataset.json>` | Evaluate an agent against an `(input, expected)` dataset |
|
|
254
255
|
| `omni export <sessionId>` | Export session history as Markdown or JSON |
|
|
255
|
-
| `omni
|
|
256
|
+
| `omni history sources\|import\|search\|show\|locate\|doctor` | Import and search third-party agent history (Claude Code, Codex) — scoped to the current project by default |
|
|
257
|
+
| `omni mcp serve` | Expose all registered skills as MCP tools over stdio (includes `search-history`, `show-history-event`) |
|
|
256
258
|
|
|
257
259
|
---
|
|
258
260
|
|
|
@@ -319,6 +321,14 @@ Skills are the tools agents call during the agentic loop. All operate within `cw
|
|
|
319
321
|
|
|
320
322
|
---
|
|
321
323
|
|
|
324
|
+
## Third-Party Agent History (`@ftarganski/omni-ai/history`)
|
|
325
|
+
|
|
326
|
+
Import, normalize and search local history from other agent harnesses (Claude Code, Codex) — 100% local, no network calls, no LLM calls. Two parsers ship out of the box (`ClaudeCodeHistoryParser`, `CodexHistoryParser`) behind a generic `IHistoryParser` contract.
|
|
327
|
+
|
|
328
|
+
On a machine with multiple projects/clients, one harness's history usually spans every project, not just the current one. `omni history search` and the `search-history`/`show-history-event` MCP skills default to the current project's scope, so an agent working in project A never sees project B's imported history unless `--all-projects` (or `allProjects: true`) is passed explicitly. Full details in [`docs/history.md`](https://github.com/Ftarganski/omni-ai/blob/main/docs/history.md).
|
|
329
|
+
|
|
330
|
+
---
|
|
331
|
+
|
|
322
332
|
## Memory & Sessions
|
|
323
333
|
|
|
324
334
|
### Via CLI
|
|
@@ -644,6 +654,7 @@ interface SessionId {
|
|
|
644
654
|
@ftarganski/omni-ai/skills/frontend ← analyze-component, analyze-module-structure…
|
|
645
655
|
@ftarganski/omni-ai/skills/qa ← analyze-test-coverage, find-test-pattern
|
|
646
656
|
@ftarganski/omni-ai/memory ← SQLiteMemoryStore, SemanticMemoryStore, compactors, VectorIndex
|
|
657
|
+
@ftarganski/omni-ai/history ← HistoryStore, IHistoryParser, searchHistorySkill, showEventSkill
|
|
647
658
|
@ftarganski/omni-ai/mcp ← createMcpServer, connectMcpSkills
|
|
648
659
|
@ftarganski/omni-ai/provider-anthropic ← AnthropicProvider
|
|
649
660
|
@ftarganski/omni-ai/provider-openai ← OpenAIProvider (+ Copilot, Groq, Ollama)
|