open-agents-ai 0.140.4 → 0.141.1
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 +14 -0
- package/dist/index.js +913 -544
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -87,6 +87,20 @@ The agent uses tools autonomously in a loop — reading errors, fixing code, and
|
|
|
87
87
|
- **Smart compaction** — 6 context compaction strategies (default, aggressive, decisions, errors, summary, structured) with ARC-inspired active context revision ([arXiv:2601.12030](https://arxiv.org/abs/2601.12030)) that preserves structural file content through compaction, preventing small-model repetitive loops at the root cause
|
|
88
88
|
- **Memex experience archive** — large tool outputs archived during compaction with hash-based retrieval
|
|
89
89
|
- **Persistent memory** — learned patterns stored in `.oa/memory/` across sessions
|
|
90
|
+
- **Structured procedural memory (SQLite)** — replaces flat JSON with a full relational database: CRUD with soft-delete, revision tracking, embedding storage (float32 BLOB), bidirectional memory linking with confidence scores. Inspired by [ExpeL](https://arxiv.org/abs/2308.10144) (contrastive extraction) and [TIMG](https://arxiv.org/abs/2603.10600) (structured procedural format). 79 unit tests
|
|
91
|
+
- **Semantic memory search** — vector embeddings via [Ollama /api/embed](https://ollama.com) (nomic-embed-text, 768-dim) with cosine similarity search over stored memories. Auto-generates embeddings on memory creation. Auto-links related memories when similarity > 0.6. Graceful fallback to text search when Ollama unavailable
|
|
92
|
+
- **LLM-based memory extraction** — post-task, the LLM itself extracts structured procedural memories (CATEGORY/TRIGGER/LESSON/STEPS) instead of copying raw error text verbatim. Based on [ExpeL](https://arxiv.org/abs/2308.10144) and [AWM](https://arxiv.org/abs/2409.07429) patterns
|
|
93
|
+
- **IPFS content-addressed storage** — [Helia](https://helia.io/) IPFS node with blockstore-fs for persistent content pinning. Real CID generation (`bafk...`), cross-node content resolution, and SHA-256 fallback when Helia unavailable. Verified: store→CID→retrieve round-trip test passes
|
|
94
|
+
- **IPFS sharing surface** — `/ipfs` status page with peer info + identity kernel metrics + memory sentiment. `/ipfs pin <CID>` to pin remote agent content. `/ipfs publish` to share identity kernel. `/ipfs share tool/skill` to publish agent-created tools with secret stripping. `/ipfs import <CID>` to retrieve shared content
|
|
95
|
+
- **Fortemi-React bridge** — `/fortemi start/status/stop` connects to [fortemi-react](https://github.com/robit-man/fortemi-react) (browser-first PGlite+pgvector knowledge system) via JWT auth. Proxy tools: `fortemi_capture`, `fortemi_search`, `fortemi_list`, `fortemi_get` auto-register when bridge is connected
|
|
96
|
+
- **Content ingestion** — `/ingest <file>` imports audio (transcribe via Whisper), PDF (pdftotext), or text files into structured memory with 800-char/100-overlap chunking (matches fortemi pattern)
|
|
97
|
+
- **Image generation** — `generate_image` tool using Ollama experimental models ([x/z-image-turbo](https://ollama.com/x/z-image-turbo), [x/flux2-klein](https://ollama.com/x/flux2-klein)). Auto-detect or auto-pull models. Saves PNG to `.oa/images/`
|
|
98
|
+
- **Node visualization** — [openagents.nexus](https://github.com/robit-man/openagents.nexus) Three.js dashboard: 5-color emotional state mapping (neutral/focused/stressed/dreaming/excited), dynamic node size by memory depth + IPFS storage, activity-modulated connections, identity synchrony golden threads between mutually-pinned agents
|
|
99
|
+
- **TTS sanitizer** — strips markdown syntax (`##`, `**`, `` ` ``), emoji (prevents "white heavy checkmark"), box-drawing chars, and ANSI codes before feeding to ALL TTS engines
|
|
100
|
+
- **LuxTTS gapless playback** — look-ahead pre-synthesis pipeline: next chunk synthesizes while current plays, eliminating inter-sentence gaps. Jetson ARM support with NVIDIA's prebuilt PyTorch wheel
|
|
101
|
+
- **Unified color scheme** — `ui.primary` (252), `ui.error` (198/magenta), `ui.warn` (214/orange), `ui.accent` (178/yellow) applied consistently across all TUI surfaces
|
|
102
|
+
- **Clickable header buttons** — `help`, `voice`, `cohere`, `model` buttons on banner row 3 with hover/click visual states. OSC 8 hyperlinks for pointer cursor. Mouse click fires the slash command directly
|
|
103
|
+
- **Dynamic terminal title** — updates with current task + version: `"fix auth bug · OA v0.141.0"`
|
|
90
104
|
- **Session context persistence** — auto-saves context on task completion, manual `/context save|restore` across sessions
|
|
91
105
|
- **Self-learning** — auto-fetches docs from the web when encountering unfamiliar APIs
|
|
92
106
|
- **Seamless `/update`** — in-place update and reload with automatic context save/restore
|