{"id":44494285,"url":"https://github.com/tashfeenahmed/scallopbot","last_synced_at":"2026-02-16T13:00:19.850Z","repository":{"id":335918428,"uuid":"1147475395","full_name":"tashfeenahmed/scallopbot","owner":"tashfeenahmed","description":"🐚 Cost-optimized personal AI assistant. Multi-provider routing, budget controls, persistent memory, voice I/O, recurring reminders. Self-hosted on your VPS.","archived":false,"fork":false,"pushed_at":"2026-02-10T03:05:31.000Z","size":2016,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-10T06:36:27.691Z","etag":null,"topics":["ai","anthropic","chatbot","clawdbot","cost-optimization","llm","moltbot","openai","openclaw","self-hosted","telegram-bot"],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tashfeenahmed.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-01T19:58:04.000Z","updated_at":"2026-02-10T03:05:35.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/tashfeenahmed/scallopbot","commit_stats":null,"previous_names":["tashfeenahmed/leanbot","tashfeenahmed/scallopbot"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/tashfeenahmed/scallopbot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tashfeenahmed%2Fscallopbot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tashfeenahmed%2Fscallopbot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tashfeenahmed%2Fscallopbot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tashfeenahmed%2Fscallopbot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tashfeenahmed","download_url":"https://codeload.github.com/tashfeenahmed/scallopbot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tashfeenahmed%2Fscallopbot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29508734,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-16T09:05:14.864Z","status":"ssl_error","status_checked_at":"2026-02-16T08:55:59.364Z","response_time":115,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","anthropic","chatbot","clawdbot","cost-optimization","llm","moltbot","openai","openclaw","self-hosted","telegram-bot"],"created_at":"2026-02-13T05:00:20.134Z","updated_at":"2026-02-16T13:00:19.841Z","avatar_url":"https://github.com/tashfeenahmed.png","language":"TypeScript","funding_links":[],"categories":["Alternatives \u0026 Competitors"],"sub_categories":["Memory for Local Models"],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/scallop.png\" alt=\"ScallopBot\" width=\"120\" height=\"120\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eScallopBot\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eA bio-inspired cognitive architecture for personal AI agents.\u003c/strong\u003e\u003cbr\u003e\n  \u003cem\u003eBridging the cognition gap in OpenClaw-compatible agent systems.\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/tashfeenahmed/scallopbot/actions/workflows/ci.yml\"\u003e\u003cimg src=\"https://img.shields.io/github/actions/workflow/status/tashfeenahmed/scallopbot/ci.yml?branch=main\u0026style=for-the-badge\u0026label=build\" alt=\"CI status\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/tashfeenahmed/scallopbot/releases\"\u003e\u003cimg src=\"https://img.shields.io/github/v/release/tashfeenahmed/scallopbot?style=for-the-badge\" alt=\"GitHub release\"\u003e\u003c/a\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge\" alt=\"MIT License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://nodejs.org\"\u003e\u003cimg src=\"https://img.shields.io/badge/node-%3E%3D22-brightgreen?style=for-the-badge\" alt=\"Node.js\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"pdf/smartbot-research-validation-2col.pdf\"\u003e\u003cstrong\u003eRead the Paper\u003c/strong\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\nOpen-source personal AI agents like [OpenClaw](https://github.com/openclaw/openclaw) excel at tool orchestration but lack genuine cognitive depth: no memory lifecycle, no self-reflection, no autonomous reasoning. ScallopBot addresses this cognition gap with a bio-inspired cognitive architecture that maintains full compatibility with the OpenClaw skill ecosystem.\n\nScallopBot runs on your own server, routes each request to the cheapest model that can handle it, tracks every cent in real time, and fails over across 7 LLM providers automatically. It connects to Telegram, Discord, WhatsApp, Slack, Signal, Matrix, a CLI, and a REST/WebSocket API -- all from a single Node.js process.\n\nThe architecture is validated against 30 research works from 2023--2026 across six domains (memory retrieval, lifecycle management, associative reasoning, sleep-inspired consolidation, affect modelling, and proactive intelligence). The full cognitive pipeline operates at an estimated **$0.06--0.10 per day**.\n\n## Benchmark Results\n\nEvaluated on the [LoCoMo](https://github.com/snap-research/locomo) long-conversation memory benchmark (1,049 QA items, 5 conversations, 138 sessions):\n\n| Metric | OpenClaw | ScallopBot | Improvement |\n|--------|:--------:|:----------:|:-----------:|\n| **F1** | 0.39 | **0.51** | +31% |\n| **Exact Match** | 0.28 | **0.32** | +14% |\n\n**F1 by question category:**\n\n| Category | OpenClaw | ScallopBot | Delta |\n|----------|:--------:|:----------:|:-----:|\n| Single-hop | 0.12 | **0.23** | +0.11 |\n| Temporal | 0.10 | **0.39** | +0.29 (4x) |\n| Open-domain | 0.11 | 0.11 | 0.00 |\n| Multi-hop | 0.34 | **0.47** | +0.13 |\n| Adversarial | **0.96** | 0.93 | -0.03 |\n\nTemporal questions show a 4x improvement driven by date-embedded memories and temporal query detection. Multi-hop benefits from memory fusion and NREM dream consolidation.\n\n## Cognitive Architecture\n\nScallopBot's cognitive layer is organised into six subsystems, orchestrated by a three-tier heartbeat daemon:\n\n| Tier | Interval | Operations |\n|------|----------|------------|\n| **Pulse** | 5 min | Health monitoring, retrieval auditing, affect EMA update |\n| **Breath** | 6 h | Decay engine, memory fusion, forgetting |\n| **Sleep** | Nightly | Dream cycle (NREM+REM), self-reflection, SOUL re-distillation, gap scanning |\n\n### Bio-Inspired Dream Cycle\n\nA two-phase sleep cycle runs during the nightly heartbeat. **NREM consolidation** clusters and merges fragmented memories across topic boundaries into coherent summaries. **REM exploration** uses high-noise spreading activation to discover non-obvious connections between memories, with an LLM judge evaluating novelty, plausibility, and usefulness of discovered associations.\n\n### Affect-Aware Interaction\n\nZero-cost emotion detection using AFINN-165 lexicon with VADER-style heuristics, mapped to the Russell circumplex model. A dual-EMA system tracks both session-level mood (2-hour half-life) and baseline mood trends (3-day half-life). An **affect guard** ensures emotional signals inform agent awareness without contaminating instructions.\n\n### Self-Reflection and SOUL Evolution\n\nNightly composite reflection analyses recent sessions across four dimensions (explanation, principles, procedures, advice). Extracted insights are merged into a living `SOUL.md` personality document, enabling continuous self-improvement through an evolving system prompt -- no model fine-tuning required.\n\n### Proactive Intelligence\n\nA gap scanner identifies unresolved questions, approaching deadlines, and behavioural anomalies. Delivery is gated by a configurable proactiveness dial (conservative/moderate/eager) and a **trust feedback loop** that calibrates future proactive behaviour based on user engagement signals.\n\n### Spreading Activation\n\nACT-R-inspired spreading activation over typed relation graphs (UPDATES, EXTENDS, DERIVES) with 3-step propagation, fan-out normalisation, and Gaussian noise to prevent deterministic retrieval. The same pure function powers both normal retrieval and REM dream exploration (with elevated noise).\n\n## Key Features\n\n### Hybrid Memory Engine\n\nSQLite-backed memory with ACID guarantees. Combines BM25 keyword scoring with semantic embeddings (Ollama/OpenAI) and optional LLM re-ranking. A complete memory lifecycle includes exponential decay with category-specific half-lives (14 days for events to 346 days for relationships), BFS-clustered fusion, and utility-based forgetting with soft-archive before hard-prune.\n\n### Cost-Aware Model Routing\n\nEvery API call is priced at the token level using a built-in pricing database covering 50+ models. A complexity analyzer scores each request and routes it to the cheapest capable tier: fast (Groq, Moonshot), standard (OpenAI, xAI), or capable (Anthropic). Daily and monthly budgets gate requests before they're sent. Provider health is tracked per-call -- consecutive failures trigger automatic failover with exponential backoff and jitter.\n\n### Local-First Voice Pipeline\n\nSpeech-to-text via faster-whisper (CTranslate2-optimized Whisper) and text-to-speech via Kokoro (82M param ONNX model) run entirely on-device with zero API cost. Cloud providers (Groq STT, OpenAI TTS) serve as automatic fallbacks. Telegram voice messages are transcribed inline; voice replies are synthesized when enabled.\n\n### Skills-Only Architecture\n\nAll capabilities -- bash, browser, file I/O, git, Docker, PDF, web search, memory -- are implemented as self-contained skills using the [OpenClaw](https://github.com/openclaw/openclaw) SKILL.md format. Skills declare their own requirements (binaries, env vars, OS) and are gated at load time. Community skills install from [ClawHub](https://clawhub.ai) with a single CLI command.\n\n## Daily Cost Breakdown\n\nAt 100 messages/day with Groq for fast-tier operations:\n\n| Operation | Calls/Day | Daily Cost |\n|-----------|:---------:|:----------:|\n| Primary conversation | 100 | $0.03 |\n| Memory re-ranking | 100 | $0.003 |\n| Relation classification | 50 | $0.002 |\n| Affect classification | 100 | $0 (lexicon) |\n| Decay/fusion (Breath ticks) | 48 | $0.005 |\n| Dream cycle (nightly) | 15--20 | $0.005 |\n| Self-reflection (nightly) | 2 | $0.002 |\n| Gap scanner (nightly) | 3--5 | $0.001 |\n| **Total** | | **$0.05--0.10** |\n\nThe entire cognitive pipeline -- dreams, reflection, affect, gap scanning -- adds approximately $0.02/day to the base conversation cost.\n\n## Quick Start\n\n```bash\ngit clone https://github.com/tashfeenahmed/scallopbot.git\ncd scallopbot\nnpm install\n\ncp .env.example .env\n# Add at least one LLM provider API key\n\nnpm run build\nnode dist/cli.js start\n```\n\nRequires Node.js 22+.\n\n## Providers\n\n| Provider | Default Model | Best For |\n|----------|--------------|----------|\n| **Anthropic** | Claude Sonnet 4 | Complex reasoning, coding |\n| **Moonshot** | Kimi K2.5 (extended thinking) | Cost-effective daily driver |\n| **OpenAI** | GPT-4o | General tasks |\n| **xAI** | Grok 4 | Real-time information |\n| **Groq** | Llama 3.3 70B | Ultra-fast inference |\n| **Ollama** | Any local model | Privacy, offline use |\n| **OpenRouter** | 100+ models | Maximum flexibility |\n\nConfigure one or more in `.env`. The router handles selection and failover automatically.\n\n## Bundled Skills\n\n16 skills ship out of the box:\n\n| Skill | Description |\n|-------|-------------|\n| `bash` | Execute shell commands |\n| `read_file` | Read file contents |\n| `write_file` | Create/overwrite files |\n| `edit_file` | Make targeted edits |\n| `browser` | Web automation ([agent-browser](https://github.com/ArcadeAI/agent-browser) from Vercel Labs) |\n| `web_search` | Search via Brave API |\n| `memory_search` | Query the hybrid memory engine |\n| `reminder` | One-time, interval, and recurring cron reminders |\n| `pdf` | Create PDFs with [Typst](https://typst.app), read with poppler, edit with qpdf |\n| `git` | Version control operations |\n| `npm` | Package management |\n| `docker` | Container management |\n| `telegram_send` | Send messages programmatically |\n| `goals` | Track and manage goals |\n| `triggers` | Define event-based triggers |\n| `progress` | Report progress to the user |\n\nInstall community skills from ClawHub:\n\n```bash\nnode dist/cli.js skill install elicitation\n```\n\n## Channels\n\n| Channel | Features |\n|---------|----------|\n| **Telegram** | Voice transcription, voice reply, file upload/download, photo analysis, per-user onboarding |\n| **Discord** | Slash commands, mention-based chat, DM support |\n| **WhatsApp** | Regular account (no Business API needed), QR auth, media support |\n| **Slack** | App-based integration |\n| **Signal** | End-to-end encrypted messaging |\n| **Matrix** | Federated chat |\n| **CLI** | Interactive terminal session with session resume (`-s \u003cid\u003e`) |\n| **REST API** | `POST /api/chat`, SSE streaming, session management, file download |\n| **WebSocket** | Real-time bidirectional communication with the web dashboard |\n\n## Web Dashboard\n\nA React + Tailwind + Vite single-page app served from the API channel. Features:\n\n- Real-time chat with markdown rendering and streaming responses\n- Debug mode showing tool execution (start/complete/error), thinking steps, and memory operations\n- Cost panel with daily/monthly budget bars, per-model breakdown, and a 14-day spending chart\n- File send/receive with download links\n- Proactive message delivery (reminders, triggers)\n\n## Configuration\n\nMinimal `.env`:\n\n```bash\nANTHROPIC_API_KEY=sk-...           # At least one provider required\nTELEGRAM_BOT_TOKEN=...             # Optional: enable Telegram\nTELEGRAM_ALLOWED_USERS=123456789   # Optional: restrict access\nBRAVE_SEARCH_API_KEY=...           # Optional: enable web search\n```\n\nBudget controls:\n\n```bash\nCOST_DAILY_BUDGET=5.00\nCOST_MONTHLY_BUDGET=100.00\nCOST_WARNING_THRESHOLD=0.8\n```\n\nFull reference: [.env.example](.env.example)\n\n## Reminders\n\nNatural language scheduling with timezone awareness:\n\n```\n\"remind me in 5 minutes to check the build\"     -\u003e Interval\n\"remind me at 10am to take medicine\"             -\u003e Absolute time\n\"remind me every day at 9am to check email\"      -\u003e Daily recurring\n\"remind me every Monday at 3pm about standup\"    -\u003e Weekly recurring\n\"remind me weekdays at 8am to exercise\"          -\u003e Weekday recurring\n```\n\nActionable reminders automatically execute when they contain action words (check, search, get, find).\n\n## Error Recovery\n\n| Failure | Response |\n|---------|----------|\n| Context overflow | Emergency compression -- summarize old messages, keep recent context |\n| Auth errors (401/403) | Rotate API keys if multiple are configured |\n| Provider outage | Automatic failover to next healthy provider |\n| Rate limits | Exponential backoff with jitter |\n| Tool crash | RecoveryManager resumes from saved state |\n| Process crash | PM2 auto-restart with crash state persistence |\n\n## Architecture\n\n```\n+-----------------------------------------------------------------+\n|                          SCALLOPBOT                              |\n+-----------------------------------------------------------------+\n|                                                                  |\n|  Telegram ---+                                                   |\n|  Discord ----+                                                   |\n|  WhatsApp ---+                                                   |\n|  Slack ------+--\u003e  GATEWAY --\u003e AGENT --\u003e ROUTER --\u003e PROVIDERS     |\n|  Signal -----+       |          |                    |           |\n|  Matrix -----+  +---------+    |         +-----------+           |\n|  CLI --------+  | Session |    |         | Anthropic |           |\n|  API/WS -----+  | Manager |    |         | Moonshot  |           |\n|                  +---------+    |         | OpenAI    |           |\n|                                 |         | xAI       |           |\n|                 +---------------+-+       | Groq      |           |\n|                 |  COGNITIVE LAYER |       | Ollama    |           |\n|                 |  Pulse | Breath  |       | OpenRouter|           |\n|                 |  Sleep | Dreams  |       +-----------+           |\n|                 +---------+-------+                               |\n|                           |                                       |\n|                 +---------+-------+                               |\n|                 | Skills | Memory |                               |\n|                 | Voice  | Affect |                               |\n|                 | Scheduler      |                                |\n|                 +----------------+                                |\n|                                                                   |\n+-------------------------------------------------------------------+\n```\n\n## Comparison with OpenClaw\n\n| Capability | OpenClaw | ScallopBot |\n|------------|----------|------------|\n| **Memory retrieval** | Vector + FTS5 hybrid | BM25 + semantic + LLM re-ranking |\n| **Memory decay** | -- | 4-factor exponential with category-specific half-lives |\n| **Memory consolidation** | -- | BFS-clustered fusion + NREM cross-category |\n| **Memory forgetting** | -- | Utility-based with soft-archive / hard-prune |\n| **Associative retrieval** | -- | Spreading activation with typed edges |\n| **Dream cycle** | -- | NREM consolidation + REM exploration |\n| **Affect detection** | -- | AFINN-165 + VADER + dual-EMA + affect guard |\n| **Self-reflection** | -- | Composite reflection + SOUL re-distillation |\n| **Proactive intelligence** | Basic Heartbeat | Gap scanner + inner thoughts + trust feedback loop |\n| **Background processing** | Heartbeat wake-up | 3-tier daemon (Pulse / Breath / Sleep) |\n| **Cost tracking \u0026 budgets** | -- | Built-in per-token tracking with daily/monthly limits |\n| **Multi-provider routing** | 2 providers | 7 providers with health-aware failover |\n| **Smart model selection** | Manual | Auto-routes by complexity |\n| **Local voice (zero cost)** | -- | Kokoro TTS + faster-whisper STT |\n| **Skill ecosystem** | 100+ bundled, 3000+ ClawHub | Full OpenClaw SKILL.md compatibility |\n| **Channel support** | 15+ platforms | 9 channels |\n| **Native apps** | macOS/iOS/Android | -- |\n\n## Deployment\n\n### One-Command Server Setup (Ubuntu 24.04)\n\n```bash\ngit clone https://github.com/tashfeenahmed/scallopbot.git /opt/scallopbot\ncd /opt/scallopbot\nbash scripts/server-install.sh    # Installs Node 22, PM2, voice deps, Ollama\ncp .env.example .env \u0026\u0026 nano .env\npm2 start ecosystem.config.cjs --env production \u0026\u0026 pm2 save\n```\n\nThe install script is idempotent and sets up:\n\n| Component | Purpose |\n|-----------|---------|\n| Node.js 22 + PM2 | Runtime and process management |\n| Python venv (kokoro-onnx, faster-whisper) | Local voice -- zero API cost TTS/STT |\n| Ollama + nomic-embed-text | Local embeddings for semantic memory search |\n| ffmpeg + sox | Audio format conversion |\n\n### Alternative: Docker\n\n```bash\ndocker build -t scallopbot .\ndocker run -d --env-file .env scallopbot\n```\n\n### Alternative: systemd\n\n```bash\nsudo tee /etc/systemd/system/scallopbot.service \u003c\u003c EOF\n[Unit]\nDescription=ScallopBot AI Assistant\nAfter=network.target\n\n[Service]\nType=simple\nUser=root\nWorkingDirectory=/opt/scallopbot\nExecStart=/usr/bin/node /opt/scallopbot/dist/cli.js start\nRestart=always\nRestartSec=10\n\n[Install]\nWantedBy=multi-user.target\nEOF\n\nsudo systemctl enable --now scallopbot\n```\n\n## CLI Reference\n\n| Command | Description |\n|---------|-------------|\n| `start` | Launch gateway with all configured channels |\n| `chat` | Interactive CLI session (`-s \u003cid\u003e` to resume) |\n| `config` | Show current configuration (`--json` for machine output) |\n| `version` | Show version |\n| `skill search \u003cquery\u003e` | Search ClawHub |\n| `skill install \u003cslug\u003e` | Install from ClawHub |\n| `skill uninstall \u003cname\u003e` | Remove a skill |\n| `skill list` | List installed skills |\n| `skill update [name]` | Update one or all skills |\n| `migrate run` | Migrate legacy JSONL memories to SQLite |\n\n## Project Structure\n\n```\nsrc/\n├── agent/          # Agent loop, session management, crash recovery\n├── channels/       # Telegram, Discord, WhatsApp, Slack, Signal, Matrix, CLI, API\n├── config/         # Zod-validated configuration schemas\n├── dashboard/      # Systemd config generator, crash recovery\n├── gateway/        # Server orchestration and channel initialization\n├── media/          # PDF, image, URL processing\n├── memory/         # Hybrid search, fact extraction, decay engine, profiles\n├── proactive/      # Unified scheduler for reminders and triggers\n├── providers/      # LLM provider implementations (7 providers)\n├── reliability/    # Circuit breaker, graceful degradation\n├── routing/        # Cost tracking, complexity analysis, model selection\n├── skills/         # Loader, registry, executor, ClawHub client (16 bundled)\n├── voice/          # STT (faster-whisper/Groq/OpenAI), TTS (Kokoro/OpenAI)\n├── cli.ts          # CLI entry point\n└── index.ts        # Library exports\n\nweb/                # React + Tailwind + Vite dashboard\n```\n\n## Development\n\n```bash\nnpm run dev           # Dev mode with hot reload\nnpm test              # Run tests (Vitest)\nnpm run typecheck     # Type check\nnpm run build         # Production build (compiles TS + builds web dashboard)\n```\n\n## Research Validation\n\nScallopBot's design decisions independently converged on patterns validated by 30 research works from 2023--2026, published at venues including ICLR, NeurIPS, CHI, and ACM TOIS. Key alignments include:\n\n- **Hybrid retrieval**: Hu et al. (memory survey), Pan et al. (SeCom, ICLR 2025)\n- **Memory lifecycle**: Alqithami (MaRS forgetting benchmark), Yang et al. (graph memory taxonomy)\n- **Spreading activation**: Pavlovic et al. (activation in RAG), Yang et al. (relational dependencies)\n- **Dream cycles**: Zhang (computational account of dreaming)\n- **Affect modelling**: Mozikov et al. (emotional prompting effects), Lu \u0026 Li (affective memory)\n- **Self-reflection**: Shinn et al. (Reflexion, 91% HumanEval), Renze \u0026 Guven (reflection taxonomy)\n- **Proactive intelligence**: Pasternak et al. (PROBE), Liu et al. (Inner Thoughts)\n\nFor the full analysis, see [the paper](pdf/smartbot-research-validation-2col.pdf).\n\n## License\n\nMIT\n\n---\n\n\u003cp align=\"center\"\u003e\n  Built by \u003ca href=\"https://github.com/tashfeenahmed\"\u003e@tashfeenahmed\u003c/a\u003e\n\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftashfeenahmed%2Fscallopbot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftashfeenahmed%2Fscallopbot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftashfeenahmed%2Fscallopbot/lists"}