A self-hosted AI coding assistant that remembers past sessions and can act across your terminal, IDE and other tools with a large context window.
Best alternatives to Decawork in 2026
Once a company's employees start building their own AI agents in tools like Claude Code or Codex, IT quickly loses track of who has access to what, which agent can touch sensitive data, and what happens when one misbehaves — a problem people are starting to call "agent sprawl." Decawork acts like a control tower for that: agents get deployed through it rather than in the shadows, so IT can approve, watch and shut down agents the same way they already manage employee laptops or software access. Under the hood, Decawork is a governance/control plane where agents built in Claude Code or Codex get deployed with scoped credentials, go through an IT approval workflow before going live, and generate a full audit log of every action they take, with automated alerting on failures or suspicious behavior. It's a Y Combinator S26 company founded by people with backgrounds in AI compliance (Barclays) and AI systems engineering (NVIDIA), which fits the specific niche it's targeting: the research cited on its own launch claims only 1 in 7 companies currently deploy AI agents with any IT approval process at all — Decawork exists to close that gap.
Quick comparison of Decawork alternatives
| # | Tool | Best for | Price |
|---|---|---|---|
| 1 | Développeurs et équipes voulant un assistant de code IA auto-hébergé avec mémoire persistante | — | |
| 2 | Développeurs construisant des agents IA en production nécessitant un contrôle fin de l'état et de la fiabilité | — | |
| 3 | Équipes produit et développeurs construisant des chatbots, agents IA ou pipelines RAG sans vouloir tout coder à la main | — | |
| 4 | Développeurs et équipes construisant des systèmes IA ancrés dans leurs propres documents (RAG), de la startup à la grande entreprise | — | |
| 5 | Développeurs et équipes techniques construisant des agents IA autonomes longue durée (recherche, code, tâches multi-étapes) | — | |
| 6 | Développeurs et équipes qui font tourner des agents de code IA (Claude Code, Cursor, Codex...) de façon semi-autonome sur une vraie codebase | — | |
| 7 | Organisations en secteurs réglementés (santé, droit, finance, gouvernement) qui ne peuvent pas envoyer leurs données à un cloud tiers | — | |
| 8 | Développeurs et ingénieurs DevOps qui veulent des agents IA légers et composables intégrés à des pipelines existants (cron, git hooks, scripts) | — | |
| 9 | Chercheurs, travailleurs du savoir et développeurs qui veulent visualiser et contrôler précisément le contexte envoyé à un LLM sur des conversations longues | — | |
| 10 | Créateurs de contenu, entrepreneurs et petites équipes qui vivent dans Telegram et veulent un assistant IA avec mémoire long terme et souveraineté des données | — | |
| 11 | Entreprises gérant de gros volumes documentaires, équipes voulant un RAG self-hosted flexible sur de multiples fournisseurs LLM | — | |
| 12 | Entreprises et équipes gérant l'accès à plusieurs fournisseurs LLM, notamment avec facturation interne ou revente | — |
- ✓ Self-hostable — code and context stay under your own control
- ✓ Persistent memory across sessions (CLI, chat, SDK)
A code library from the LangChain team for building AI agents that can pause, remember where they were, and pick back up later — even after a server restart — instead of losing all progress if something goes wrong mid-task.
- ✓ Durable execution — resumes from a checkpoint instead of restarting after failure
- ✓ Native human-in-the-loop and short/long-term memory primitives
An open-source platform for building AI chatbots and automated workflows by connecting blocks on a canvas, instead of writing code from scratch.
- ✓ Visual builder for AI workflows (RAG, agents, conditional logic) is genuinely productive
- ✓ Open-source and self-hostable — no forced cloud lock-in
An open-source toolkit for building AI systems that answer questions using your own documents — feeding an AI model your company's PDFs, wikis, or support tickets so it answers from real content instead of guessing.
- ✓ Modular, composable pipelines — swap vector DBs or LLM providers without a rebuild
- ✓ Broad connector support across major vector databases and LLM providers
An open-source framework from ByteDance for building AI agents that can spend minutes or hours working through a task — researching, writing code, and spinning up helper agents — rather than answering in one quick reply.
- ✓ Large scale and maturity — 80k+ GitHub stars, backed by ByteDance
- ✓ Sandboxed execution (local/Docker/Kubernetes) treated as a real security concern
A guardrail system that limits which tools an AI coding agent can use at each stage of a task — read-only while planning, edit access only while implementing — so it can't take an action outside its current job.
- ✓ Deterministic enforcement outside the LLM — can't be prompted around
- ✓ Per-phase tool restrictions reduce blast radius of agent mistakes
A free, open-source, self-hosted AI agent platform built for organizations that can't send data to a third-party cloud — think law firms, clinics or banks — with role-based access, memory, and support for every major AI model.
- ✓ Fully self-hosted end to end — no data ever leaves your infrastructure
- ✓ Role-based access with PostgreSQL Row Level Security, native multi-user support
A free, open-source command-line tool that lets you define small, single-purpose AI agents as simple config files and run them like Unix programs — triggered from the terminal, a cron job, a git hook, or piped straight into another command.
- ✓ 12MB binary, no daemon or GUI — drops straight into existing pipelines
- ✓ Agents defined in version-controllable TOML, easy to code-review
A free, open-source infinite canvas that turns your conversations with AI models into an editable graph — so you can see, prune, and reuse exactly which parts of the conversation the AI is actually reading, instead of a single ever-growing chat thread.
- ✓ Context is visible and editable as a graph, instead of an opaque chat thread
- ✓ Free and open source (MIT), self-hostable or usable via the web demo
A self-hosted AI assistant that lives inside Telegram on your own server, with memory, emotional awareness, and dozens of built-in skills — useful if you want an AI that remembers your life and work without handing your data to a big tech company.
- ✓ 4-layer memory with full-text + vector search — remembers context long-term, unlike typical chatbots
- ✓ 50+ pre-installed skills via MCP, directly inside Telegram (voice and files included)
An open-source, self-hosted platform from Tencent that turns a pile of company documents into a searchable knowledge base with AI Q&A — built to plug into a very wide range of AI models and vector databases.
- ✓ Supports 20+ LLM providers and 8+ vector databases — no vendor lock-in
- ✓ ReACT multi-step reasoning agents with 29 official MCP tools, beyond simple Q&A
A free, open-source self-hosted gateway that puts a single API in front of a dozen different AI providers (OpenAI, Claude, Gemini and more), with built-in usage tracking and billing — useful if you're reselling or managing AI access for a team or product.
- ✓ Single gateway for 10+ LLM providers, OpenAI/Claude/Gemini-compatible
- ✓ Built-in organization accounts, permissions, and per-user usage/cost tracking
FAQ about Decawork alternatives
- What is the best alternative to Decawork in 2026?
- Based on our selection, Dropstone is the best alternative to Decawork in 2026. A self-hosted AI coding assistant that remembers past sessions and can act across your terminal, IDE and other tools with a large context window.. See our full ranking above to compare all options.
- Is Decawork free?
- Decawork is a paid tool. Several alternatives in our selection offer free or freemium versions.
- How many alternatives to Decawork are there?
- mySelectas has listed 12 alternatives to Decawork in the AI & Machine Learning category. Our selection is updated regularly to include the best options available.